Models

All models

Every model listed in tt-inference-server or published as a tt-model bundle. Complete models come first, then Functional, then Experimental, then community bundles.

Community models are tt-model bundles published by their owners and are not in tt-inference-server's release spec. Tenstorrent has not reviewed them. Serve at your own risk.

132 models
LLMOfficial

DeepSeek-R1-Distill-Llama-70B

deepseek-ai/DeepSeek-R1-Distill-Llama-70B

Listed in tt-inference-server on 5 hardware types; best status Complete.

Runs on
BH 4xP150, BH LoudBox, BH QuietBox 2 +2
Status
Complete
tt launch
7 clients
70B parameters
Speech-to-textOfficial

distil-large-v3

distil-whisper/distil-large-v3

Listed in tt-inference-server on 6 hardware types; best status Complete.

Runs on
BH QuietBox 2, WH Galaxy, WH LoudBox/QuietBox +3
Status
Complete
tt launch
None
Image generationOfficial

FLUX.1-dev

black-forest-labs/FLUX.1-dev

Listed in tt-inference-server on 6 hardware types; best status Complete.

Runs on
BH 4xP150, BH LoudBox, BH P300 +3
Status
Complete
tt launch
None
Image generationOfficial

FLUX.1-schnell

black-forest-labs/FLUX.1-schnell

Listed in tt-inference-server on 6 hardware types; best status Complete.

Runs on
BH 4xP150, BH LoudBox, BH P300 +3
Status
Complete
tt launch
None
LLMOfficial

gemma-4-12B-it

google/gemma-4-12B-it

Listed in tt-inference-server on 2 hardware types; best status Complete. 1 tt-model bundle also published.

Runs on
BH Galaxy, BH QuietBox 2, p100 +1
Status
Complete
tt launch
7 clients
12B parameters1 tt-model bundle
LLMOfficial

gemma-4-31B-it

google/gemma-4-31B-it

Listed in tt-inference-server on 2 hardware types; best status Complete.

Runs on
BH Galaxy, BH QuietBox 2
Status
Complete
tt launch
7 clients
31B parameters
LLMOfficial

Llama-3.1-70B

meta-llama/Llama-3.1-70B

Listed in tt-inference-server on 5 hardware types; best status Complete.

Runs on
BH 4xP150, BH LoudBox, BH QuietBox 2 +2
Speed
≥ 10 tok/s≤ 238 ms WH Galaxy
Status
Complete
tt launch
7 clients
70B parameters
LLMOfficial

Llama-3.1-70B-Instruct

meta-llama/Llama-3.1-70B-Instruct

Listed in tt-inference-server on 5 hardware types; best status Complete.

Runs on
BH 4xP150, BH LoudBox, BH QuietBox 2 +2
Speed
≥ 9.5 tok/s≤ 226 ms WH Galaxy
Status
Complete
tt launch
7 clients
70B parameters
LLMOfficial

Llama-3.1-8B

meta-llama/Llama-3.1-8B

Listed in tt-inference-server on 8 hardware types; best status Complete.

Runs on
BH LoudBox, BH P300, BH QuietBox 2 +5
Speed
≥ 85 tok/s≤ 46 ms WH LoudBox/QuietBox
Status
Complete
tt launch
7 clients
8B parameters
LLMOfficial

Llama-3.1-8B-Instruct

meta-llama/Llama-3.1-8B-Instruct

Listed in tt-inference-server on 9 hardware types; best status Complete.

Runs on
BH LoudBox, BH P300, BH QuietBox 2 +6
Speed
≥ 36 tok/s≤ 58 ms WH LoudBox/QuietBox
Status
Complete
tt launch
7 clients
8B parameters
LLMOfficial

Llama-3.3-70B-Instruct

meta-llama/Llama-3.3-70B-Instruct

Listed in tt-inference-server on 5 hardware types; best status Complete.

Runs on
BH 4xP150, BH LoudBox, BH QuietBox 2 +2
Speed
≥ 14 tok/s≤ 76 ms WH Galaxy
Status
Complete
tt launch
7 clients
70B parameters
LLMOfficial

Mistral-7B-Instruct-v0.3

mistralai/Mistral-7B-Instruct-v0.3

Listed in tt-inference-server on 3 hardware types; best status Complete.

Runs on
WH LoudBox/QuietBox, n150, n300
Speed
≥ 35 tok/s≤ 156 ms n150
Status
Complete
tt launch
2 clients
7B parameters
CNNOfficial

mobilenetv2

mobilenetv2

Listed in tt-inference-server on 2 hardware types; best status Complete.

Runs on
n150, n300
Status
Complete
tt launch
None
Video generationOfficial

mochi-1-preview

genmo/mochi-1-preview

Listed in tt-inference-server on 3 hardware types; best status Complete.

Runs on
BH LoudBox, WH Galaxy, WH LoudBox/QuietBox
Status
Complete
tt launch
None
LLMOfficial

Qwen3-32B

Qwen/Qwen3-32B

Listed in tt-inference-server on 5 hardware types; best status Complete. 3 tt-model bundles also published.

Runs on
BH 4xP150, BH Galaxy, BH LoudBox +4
Speed
≥ 78 tok/s≤ 60 ms WH Galaxy
Status
Complete
tt launch
7 clients
32B parameters3 tt-model bundles
LLMOfficial

Qwen3.8-27B

Qwen/Qwen3.8-27B

Listed in tt-inference-server on 1 hardware type; best status Complete. 3 tt-model bundles also published.

Runs on
BH 4xP150, BH QuietBox 2, p150x2
Speed
≥ 20 tok/s≤ 124 ms BH QuietBox 2
Status
Complete
tt launch
7 clients
27B parameters3 tt-model bundles
Image generationOfficial

stable-diffusion-3.5-large

stabilityai/stable-diffusion-3.5-large

Listed in tt-inference-server on 2 hardware types; best status Complete.

Runs on
WH Galaxy, WH LoudBox/QuietBox
Status
Complete
tt launch
None
Image generationOfficial

stable-diffusion-xl-base-1.0

stabilityai/stable-diffusion-xl-base-1.0

Listed in tt-inference-server on 4 hardware types; best status Complete.

Runs on
WH Galaxy, WH LoudBox/QuietBox, n150 +1
Status
Complete
tt launch
None
Image generationOfficial

stable-diffusion-xl-base-1.0-img-2-img

stabilityai/stable-diffusion-xl-base-1.0-img-2-img

Listed in tt-inference-server on 4 hardware types; best status Complete.

Runs on
WH Galaxy, WH LoudBox/QuietBox, n150 +1
Status
Complete
tt launch
None
CNNOfficial

vit

vit

Listed in tt-inference-server on 2 hardware types; best status Complete.

Runs on
n150, n300
Status
Complete
tt launch
None
CNNOfficial

vovnet

vovnet

Listed in tt-inference-server on 2 hardware types; best status Complete.

Runs on
n150, n300
Status
Complete
tt launch
None
Video generationOfficial

Wan2.2-T2V-A14B-Diffusers

Wan-AI/Wan2.2-T2V-A14B-Diffusers

Listed in tt-inference-server on 6 hardware types; best status Complete.

Runs on
BH 4xP150, BH Galaxy, BH LoudBox +3
Status
Complete
tt launch
None
14B parameters
Speech-to-textOfficial

whisper-large-v3

openai/whisper-large-v3

Listed in tt-inference-server on 6 hardware types; best status Complete.

Runs on
BH QuietBox 2, WH Galaxy, WH LoudBox/QuietBox +3
Status
Complete
tt launch
None
CNNOfficial

yolox_nano

yolox_nano

Listed in tt-inference-server on 1 hardware type; best status Complete.

Runs on
p150
Status
Complete
tt launch
None
LLMOfficial

Llama-3.2-1B

meta-llama/Llama-3.2-1B

Listed in tt-inference-server on 3 hardware types; best status Functional.

Runs on
WH LoudBox/QuietBox, n150, n300
Speed
≥ 18 tok/s≤ 60 ms WH LoudBox/QuietBox
Status
Functional
tt launch
7 clients
1B parameters
LLMOfficial

Llama-3.2-1B-Instruct

meta-llama/Llama-3.2-1B-Instruct

Listed in tt-inference-server on 3 hardware types; best status Functional.

Runs on
WH LoudBox/QuietBox, n150, n300
Speed
≥ 36 tok/s≤ 70 ms WH LoudBox/QuietBox
Status
Functional
tt launch
7 clients
1B parameters
LLMOfficial

Llama-3.2-3B

meta-llama/Llama-3.2-3B

Listed in tt-inference-server on 3 hardware types; best status Functional.

Runs on
WH LoudBox/QuietBox, n150, n300
Speed
≥ 6.1 tok/s≤ 170 ms WH LoudBox/QuietBox
Status
Functional
tt launch
7 clients
3B parameters
LLMOfficial

Llama-3.2-3B-Instruct

meta-llama/Llama-3.2-3B-Instruct

Listed in tt-inference-server on 3 hardware types; best status Functional. 1 tt-model bundle also published.

Runs on
WH LoudBox/QuietBox, n150, n300 +2
Speed
≥ 17 tok/s≤ 120 ms WH LoudBox/QuietBox
Status
Functional
tt launch
7 clients
3B parameters1 tt-model bundle
LLMOfficial

Qwen2.5-72B

Qwen/Qwen2.5-72B

Listed in tt-inference-server on 2 hardware types; best status Functional.

Runs on
WH Galaxy, WH LoudBox/QuietBox
Speed
≥ 8.2 tok/s≤ 130 ms WH Galaxy
Status
Functional
tt launch
7 clients
72B parameters
LLMOfficial

Qwen2.5-72B-Instruct

Qwen/Qwen2.5-72B-Instruct

Listed in tt-inference-server on 2 hardware types; best status Functional.

Runs on
WH Galaxy, WH LoudBox/QuietBox
Speed
≥ 7.1 tok/s≤ 510 ms WH Galaxy
Status
Functional
tt launch
7 clients
72B parameters
LLMOfficial

Qwen3-8B

Qwen/Qwen3-8B

Listed in tt-inference-server on 4 hardware types; best status Functional.

Runs on
WH Galaxy, WH LoudBox/QuietBox, n150 +1
Speed
≥ 60 tok/s≤ 120 ms WH Galaxy
Status
Functional
tt launch
7 clients
8B parameters
VLMOfficial

Qwen3-VL-32B-Instruct

Qwen/Qwen3-VL-32B-Instruct

Listed in tt-inference-server on 1 hardware type; best status Functional.

Runs on
WH LoudBox/QuietBox
Speed
≥ 3.8 tok/s≤ 1.5 s WH LoudBox/QuietBox
Status
Functional
tt launch
2 clients
32B parameters
LLMOfficial

QwQ-32B

Qwen/QwQ-32B

Listed in tt-inference-server on 2 hardware types; best status Functional.

Runs on
WH Galaxy, WH LoudBox/QuietBox
Speed
≥ 16 tok/s≤ 300 ms WH Galaxy
Status
Functional
tt launch
7 clients
32B parameters
CNNOfficial

resnet-50

resnet-50

Listed in tt-inference-server on 2 hardware types; best status Functional.

Runs on
n150, n300
Status
Functional
tt launch
None
CNNOfficial

segformer

segformer

Listed in tt-inference-server on 2 hardware types; best status Functional.

Runs on
n150, n300
Status
Functional
tt launch
None
Image generationOfficial

Z-Image-Turbo

Tongyi-MAI/Z-Image-Turbo

Listed in tt-inference-server on 1 hardware type; best status Functional. 1 tt-model bundle also published.

Runs on
BH QuietBox 2, p100a
Status
Functional
tt launch
None
1 tt-model bundle
LLMOfficial

AFM-4.5B

arcee-ai/AFM-4.5B

Listed in tt-inference-server on 2 hardware types; best status Experimental.

Runs on
WH LoudBox/QuietBox, n300
Status
Experimental
tt launch
2 clients
4B parameters
EmbeddingOfficial

bge-large-en-v1.5

BAAI/bge-large-en-v1.5

Listed in tt-inference-server on 4 hardware types; best status Experimental.

Runs on
WH Galaxy, WH LoudBox/QuietBox, n150 +1
Status
Experimental
tt launch
None
EmbeddingOfficial

bge-m3

BAAI/bge-m3

Listed in tt-inference-server on 1 hardware type; best status Experimental.

Runs on
BH QuietBox 2
Status
Experimental
tt launch
None
LLMOfficial

DeepSeek-R1-0528

deepseek-ai/DeepSeek-R1-0528

Listed in tt-inference-server on 3 hardware types; best status Experimental.

Runs on
Dual WH Galaxy, Quad WH Galaxy, WH Galaxy
Status
Experimental
tt launch
7 clients
LLMOfficial

diffusiongemma-26B-A4B-it

google/diffusiongemma-26B-A4B-it

Listed in tt-inference-server on 1 hardware type; best status Experimental.

Runs on
BH QuietBox 2
Status
Experimental
tt launch
2 clients
4B parameters
VLMOfficial

gemma-3-27b-it

google/gemma-3-27b-it

Listed in tt-inference-server on 1 hardware type; best status Experimental.

Runs on
WH Galaxy
Speed
≥ 4.3 tok/s≤ 760 ms WH Galaxy
Status
Experimental
tt launch
2 clients
27B parameters
LLMOfficial

gpt-oss-120b

openai/gpt-oss-120b

Listed in tt-inference-server on 4 hardware types; best status Experimental. 3 tt-model bundles also published.

Runs on
BH 4xP150, BH Galaxy, BH LoudBox +3
Speed
≥ 2.7 tok/s≤ 510 ms BH QuietBox 2
Status
Experimental
tt launch
7 clients
120B parameters3 tt-model bundles
EmbeddingOfficial

Qwen3-Embedding-0.6B

Qwen/Qwen3-Embedding-0.6B

Listed in tt-inference-server on 1 hardware type; best status Experimental.

Runs on
BH QuietBox 2
Status
Experimental
tt launch
None
EmbeddingOfficial

Qwen3-Embedding-4B

Qwen/Qwen3-Embedding-4B

Listed in tt-inference-server on 1 hardware type; best status Experimental.

Runs on
BH QuietBox 2
Status
Experimental
tt launch
None
4B parameters
EmbeddingOfficial

Qwen3-Embedding-8B

Qwen/Qwen3-Embedding-8B

Listed in tt-inference-server on 4 hardware types; best status Experimental.

Runs on
WH Galaxy, WH LoudBox/QuietBox, n150 +1
Status
Experimental
tt launch
None
8B parameters
LLMOfficial

Qwen3.6-27B

Qwen/Qwen3.6-27B

Listed in tt-inference-server on 1 hardware type; best status Experimental. 1 tt-model bundle also published.

Runs on
BH 4xP150, BH QuietBox 2
Status
Experimental
tt launch
7 clients
27B parameters1 tt-model bundle
Text-to-speechOfficial

speecht5_tts

microsoft/speecht5_tts

Listed in tt-inference-server on 2 hardware types; best status Experimental.

Runs on
BH QuietBox 2, p150
Status
Experimental
tt launch
None
Text to audio (inferred)Community model

Ace-Step1.5

ACE-Step/Ace-Step1.5

Published as 1 tt-model bundle by sunandbean.

Runs on
p100a
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Robotics (inferred)Community model

Alpamayo2-Super

nvidia/Alpamayo2-Super

Published as 1 tt-model bundle by changh95.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Object detectionCommunity model

bevformer-small-weights

changh95/bevformer-small-weights

BEVFormer-small, a 59.5M-parameter camera-only 3D detector (ResNet-101 with deformable convolutions in stages 3 and 4 and a one-level FPN, a 3-layer spatiotemporal BEV encoder over a 150x150 bird's-eye view that attends to the previous…

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Object detectionCommunity model

bevfusion

AutowareFoundation/bevfusion

BEVFusion-L, the lidar-only model of the weights repo (bevfusionlidar.onnx, 8.3M parameters): hard voxelization (0.17 x 0.17 x 0.2 m voxels on a 1440 x 1440 x 41 grid) with a mean voxel encoder, a 21-layer sparse 3D convolution encoder to…

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Object detectionCommunity model

camera_streampetr

AutowareFoundation/camera_streampetr

StreamPETR, an 82M-parameter camera-only 3D detector with a temporal object memory: a VoVNet-99-eSE + CPFPN image backbone on five cameras at 480x640, the PETR 3D position embedding (computed once per calibration) and a 6-layer transformer…

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Decision modelCommunity model

clef

Cloudflare/clef

Clef is a 27B-parameter multimodal decision model from Cloudflare: a Qwen3.8-27B backbone (64 layers, 48 Gated DeltaNet and 16 full-attention, hidden size 5120) with its 27-block vision tower, and a 65M-parameter joint schema head.

Runs on
p150x2
Status
Not in the release spec
tt launch
None
2 tt-model bundles
Decision modelCommunity model

clm-v0.1-8b

Qwen/Qwen3-8B

CLM-v0.1-8B is a System One verifier and ranker: a frozen Qwen3-8B encoder (36 layers, last-token pooling) with two 9.4M-parameter MLP projection heads (4096-1536-1536-512), a state head and an action head, trained with a bidirectional…

Runs on
BH 4xP150, p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Depth and 3D geometry (inferred)Community model

DA3Metric-Large

depth-anything/DA3Metric-Large

Published as 1 tt-model bundle by changh95.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
LLM (inferred)Community model

DeepSeek-V4.1-Flash

deepseek-ai/DeepSeek-V4.1-Flash

Published as 1 tt-model bundle by rothgar.

Runs on
BH QuietBox 2
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Text to audio (inferred)Community model

DiffRhythm-1_2-full

ASLP-lab/DiffRhythm-1_2-full

Published as 1 tt-model bundle by sunandbean.

Runs on
p100a
Status
Not in the release spec
tt launch
None
1 tt-model bundle
RoboticsCommunity model

diffusion_planner

AutowareFoundation/diffusion_planner

Diffusion Planner v5.0, a 14.55M-parameter diffusion-transformer planner: six MLP-Mixer entity encoders and a 6-block transformer fusion encoder over 564 scene tokens, a 3-block DiT decoder with adaLN (self-attention over the ego and 320…

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Depth and 3D geometry (inferred)Community model

DUSt3R_ViTLarge_BaseDecoder_512_dpt

naver/DUSt3R_ViTLarge_BaseDecoder_512_dpt

Published as 1 tt-model bundle by changh95.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
LLMCommunity model

ELYZA-Thinking-1.0-llm-jp-4-33b

elyza/ELYZA-Thinking-1.0-llm-jp-4-33b

elyza/ELYZA-Thinking-1.0-llm-jp-4-33b (ELYZA-Thinking 1.0, a reasoning model post-trained by ELYZA on llm-jp/llm-jp-4-33b-base) served by vLLM and the Tenstorrent vLLM plugin on a QuietBox 2 (two p300c boards, four Blackhole chips, mesh…

Runs on
BH QuietBox 2
Speed
21 tok/s293 ms 4 chips
Status
Not in the release spec
tt launch
7 clients
1 tt-model bundle
EmbeddingCommunity model

embeddinggemma-2

google/embeddinggemma-2

EmbeddingGemma 2, a multimodal embedding model.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
LLM (inferred)Community model

EXAONE-4.5-33B

LGAI-EXAONE/EXAONE-4.5-33B

Published as 1 tt-model bundle by changh95.

Runs on
BH LoudBox
Status
Not in the release spec
tt launch
7 clients
1 tt-model bundle
Image generation (inferred)Community model

FLUX.2-dev

black-forest-labs/FLUX.2-dev

Published as 1 tt-model bundle by stisiTT.

Runs on
BH QuietBox 2
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Image generation (inferred)Community model

FLUX.2-klein-4B

black-forest-labs/FLUX.2-klein-4B

Published as 1 tt-model bundle by sunandbean.

Runs on
p100a
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Computer vision (inferred)Community model

gaze-lle-weights

changh95/gaze-lle-weights

Published as 1 tt-model bundle by changh95.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
LLMCommunity model

gemma-4-26B-A4B-it

google/gemma-4-26B-A4B-it

Gemma 4 26B A4B instruction-tuned, a 25.2B-parameter mixture-of-experts model (3.8B active parameters; 30 layers; 128 experts with 8 active plus 1 shared), served with vLLM for chat, reasoning and tool calling on text input.

Runs on
BH 4xP150, p150, p150x2
Speed
37 tok/s175 ms 1 chip
Status
Not in the release spec
tt launch
7 clients
1 tt-model bundle
LLM (inferred)Community model

GLM-4.5-Air

zai-org/GLM-4.5-Air

Published as 1 tt-model bundle by raahemnabeel.

Runs on
BH 4xP150, BH P300, BH QuietBox 2 +1
Status
Not in the release spec
tt launch
7 clients
1 tt-model bundle
LLM (inferred)Community model

GLM-5.3-Flash

zai-org/GLM-5.3-Flash

Published as 1 tt-model bundle by raahemnabeel.

Runs on
BH 4xP150, BH QuietBox 2
Status
Not in the release spec
tt launch
7 clients
1 tt-model bundle
LLMCommunity model

gpt-oss-20b

openai/gpt-oss-20b

gpt-oss-20b, OpenAI's 21B-parameter mixture-of-experts reasoning model (3.6B active parameters), served with vLLM for chat, reasoning and function calling.

Runs on
BH 4xP150, BH LoudBox, p150 +1
Speed
48 tok/s209 ms 1 chip
Status
Not in the release spec
tt launch
7 clients
4 tt-model bundles
Robotics (inferred)Community model

GR00T-N1.5-3B

nvidia/GR00T-N1.5-3B

Published as 1 tt-model bundle by changh95.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Robotics (inferred)Community model

GR00T-N1.6-3B

nvidia/GR00T-N1.6-3B

Published as 1 tt-model bundle by changh95.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Robotics (inferred)Community model

GR00T-N1.7-3B

nvidia/GR00T-N1.7-3B

Published as 1 tt-model bundle by changh95.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Computer vision (inferred)Community model

hamer-weights

changh95/hamer-weights

Published as 1 tt-model bundle by changh95.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Image generation (inferred)Community model

HiDream-O1-Image

HiDream-ai/HiDream-O1-Image

Published as 1 tt-model bundle by sunandbean.

Runs on
p100a
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Object detectionCommunity model

image_projection_based_fusion

AutowareFoundation/image_projection_based_fusion

PointPainting, a camera-LiDAR 3D object detector: the 2-D detections (ROIs) of up to 8 rectified cameras are projected onto the LiDAR points as 3 additive class bits, then a PointPillars pillar encoder (PFN 12-16-32), a SECOND backbone, a…

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
LLM (inferred)Community model

Kimi-Linear-48B-A3B-Instruct

moonshotai/Kimi-Linear-48B-A3B-Instruct

Published as 1 tt-model bundle by jashansinghTT.

Runs on
BH P300, BH QuietBox 2
Status
Not in the release spec
tt launch
7 clients
1 tt-model bundle
LLM (inferred)Community model

Laguna-S-2.1

poolside/Laguna-S-2.1

Published as 1 tt-model bundle by mando2222.

Runs on
BH 4xP150
Status
Not in the release spec
tt launch
2 clients
1 tt-model bundle
LLMCommunity model

Laguna-XS-2.1

poolside/Laguna-XS-2.1

Laguna-XS-2.1, poolside's 33B-parameter mixture-of-experts coding model (3B active parameters), served with vLLM with tool calling and separated reasoning output.

Runs on
BH 4xP150, p150x2
Speed
20 tok/s215 ms 2 chips
Status
Not in the release spec
tt launch
7 clients
1 tt-model bundle
Decision modelCommunity model

laya

convaiinnovations/laya

Laya is a 421M-parameter non-LLM calibrated decision model: a ModernBERT-large encoder (28 layers, 1024 hidden, GeGLU, dual-theta RoPE, one global attention layer per three) with a 2-layer decision head that has an option-marker scorer and…

Runs on
BH 4xP150, p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Decision modelCommunity model

laya-typed-decisions

convaiinnovations/laya-typed-decisions

Laya typed-decisions is the authors' fine-tune of Laya on the LocalLLaMA/typed-decisions train split: a 421M-parameter ModernBERT-large encoder (28 layers, 1024 hidden, GeGLU, dual-theta RoPE, one global attention layer per three) with a…

Runs on
BH 4xP150, p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
LLM (inferred)Community model

LFM2.5-24B-A2B

LiquidAI/LFM2.5-24B-A2B

A 24B-parameter mixture-of-experts model with 2B active parameters per token: a hybrid decoder of 30 gated short-convolution layers and 10 grouped-query attention layers.

Runs on
BH 4xP150
Speed
107 tok/s 4 chips
Status
Not in the release spec
tt launch
7 clients
1 tt-model bundle
Object detectionCommunity model

lidar_centerpoint

AutowareFoundation/lidar_centerpoint

CenterPoint, the LiDAR 3D object detector Autoware runs by default, and its CenterPoint-tiny variant: a PointPillars pillar encoder (PFN 9-16-32), a SECOND backbone, a SECONDFPN neck and a single-task CenterPoint head, on a 480x480 head…

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Image segmentationCommunity model

lidar_frnet

AutowareFoundation/lidar_frnet

FRNet, a 10.0M-parameter LiDAR semantic-segmentation network (a frustum feature encoder of point-wise MLPs with a per-cell max, a frustum-range 2D CNN with four residual stages and point-pixel fusion, and a per-point head), one network per…

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Object detectionCommunity model

lidar_transfusion

AutowareFoundation/lidar_transfusion

TransFusion-L (t4xx190m), the LiDAR-only TransFusion detector of Autoware's opt-in lidartransfusion node: a PointPillars pillar encoder (11 decorated features, PFN 32-64) on a 768x768 pillar grid, a SECOND backbone, a SECONDFPN neck and a…

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
LLMCommunity model

llm-jp-4-33b-thinking

llm-jp/llm-jp-4-33b-thinking

llm-jp/llm-jp-4-33b-thinking (LLM-jp-4 33B, thinking) served by vLLM and the Tenstorrent vLLM plugin on a QuietBox 2 (two p300c boards, four Blackhole chips, mesh P300x2).

Runs on
BH QuietBox 2
Speed
20 tok/s342 ms 4 chips
Status
Not in the release spec
tt launch
2 clients
1 tt-model bundle
LLMCommunity model

llm-jp-4-8b-thinking

llm-jp/llm-jp-4-8b-thinking

llm-jp/llm-jp-4-8b-thinking (LLM-jp-4 8B, thinking) served by vLLM and the Tenstorrent vLLM plugin on one Blackhole P150 chip (p150a).

Runs on
p150
Speed
22 tok/s311 ms 1 chip
Status
Not in the release spec
tt launch
2 clients
1 tt-model bundle
LLMCommunity model

llm-jp-4.1-8b-thinking

llm-jp/llm-jp-4.1-8b-thinking

llm-jp/llm-jp-4.1-8b-thinking (LLM-jp-4.1 8B, thinking) served by vLLM and the Tenstorrent vLLM plugin on one Blackhole P150 chip (p150a).

Runs on
p150
Status
Not in the release spec
tt launch
7 clients
1 tt-model bundle
Object detection (inferred)Community model

LocateAnything-3B

nvidia/LocateAnything-3B

Published as 1 tt-model bundle by changh95.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
RoboticsCommunity model

meteor

AutowareFoundation/meteor

METEOR v157, a 48.25M-parameter camera-only perception and planning network (a ResNet-34 + FPN image encoder over the eight cameras, 2D segmentation, depth, 2D detection and traffic-light heads, a depth-gated lift to one 800x500 bird's-eye…

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
LLM (inferred)Community model

MiMo-V2.6-Distill-Qwen-9B

XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B

Published as 1 tt-model bundle by ndaly.

Runs on
p150
Status
Not in the release spec
tt launch
2 clients
1 tt-model bundle
Image text to videoCommunity model

MiniMax-H3

MiniMaxAI/MiniMax-H3

MiniMax-H3 on Tenstorrent Blackhole: a 50-block diffusion transformer that generates video and the matching stereo soundtrack in one pass, conditioned by a Qwen3-VL-32B text/vision encoder.

Runs on
BH QuietBox 2, p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Text to audioCommunity model

MiniMax-Music3

MiniMaxAI/MiniMax-Music3

MiniMax Music 3, a lyrics-and-caption conditioned music generation model (8B Qwen3-based global LLM, 0.6B depth decoder for the residual RVQ codebooks, 2.4B flow-matching DiT and a DAC-style vocoder), with an SGLang-Omni compatible…

Runs on
p100, p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
LLM (inferred)Community model

Mistral-Small-4-119B-2603

mistralai/Mistral-Small-4-119B-2603

Published as 1 tt-model bundle by ndaly.

Runs on
BH QuietBox 2
Status
Not in the release spec
tt launch
2 clients
1 tt-model bundle
Depth and 3D geometry (inferred)Community model

moge-2-vitl-normal

Ruicheng/moge-2-vitl-normal

Published as 1 tt-model bundle by changh95.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
LLM (inferred)Community model

Motif-3

Motif-Technologies/Motif-3

Published as 1 tt-model bundle by changh95.

Runs on
BH Galaxy
Status
Not in the release spec
tt launch
None
1 tt-model bundle
LLMCommunity model

Muse-Glimmer-30B

meta-models/Muse-Glimmer-30B

Muse-Glimmer-30B, a dense transformer of about 29.6B parameters including its vision encoder, served with vLLM as a text-only endpoint for long-context agentic coding with tool calling and separated reasoning output.

Runs on
BH QuietBox 2
Speed
42 tok/s70 ms 4 chips
Status
Not in the release spec
tt launch
7 clients
1 tt-model bundle
LLM (inferred)Community model

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4

nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4

NVIDIA Nemotron 3.5 Lightning 30B-A3B (NVFP4 checkpoint), a hybrid Mamba-Transformer mixture-of-experts reasoning model with a 1,048,576-token context, ported to Tenstorrent Blackhole and served through stock vLLM 0.26.0 plus the…

Runs on
BH QuietBox 2
Status
Not in the release spec
tt launch
7 clients
1 tt-model bundle
LLMCommunity model

Olmo-3.1-32B-Instruct

allenai/Olmo-3.1-32B-Instruct

Olmo 3.1 32B Instruct, a fully open 32B dense decoder with hybrid sliding-window / full attention and 65k context, served with vLLM.

Runs on
BH P300, BH QuietBox 2, p150
Speed
11 tok/s177 ms 1 chip
Status
Not in the release spec
tt launch
7 clients
1 tt-model bundle
LLMCommunity model

Ornith-1.0-35B

ornith-ai/Ornith-1.0-35B

Ornith-1.0-35B, a 35B-parameter mixture-of-experts model for agentic reasoning and coding, served with vLLM with tool calling and separated reasoning output.

Runs on
BH 4xP150, p100, p150 +1
Speed
12 tok/s253 ms 1 chip
Status
Not in the release spec
tt launch
7 clients
1 tt-model bundle
LLM (inferred)Community model

Ornith-1.5-122B

ornith-ai/Ornith-1.5-122B

Ornith-1.5-122B, a 122B-parameter mixture-of-experts model with 10B parameters active per token (256 experts, top-8 plus a shared expert; 48 layers mixing Gated DeltaNet linear attention with gated full attention; the Qwen3.5-122B-A10B…

Runs on
BH 4xP150, BH QuietBox 2
Speed
133 tok/s230 ms 4 chips
Status
Not in the release spec
tt launch
7 clients
1 tt-model bundle
LLM (inferred)Community model

Ornith-1.5-35B-A3B

ornith-ai/Ornith-1.5-35B-A3B

Ornith-1.5-35B-A3B (35B total / 3B active MoE: 256 experts, top-8 + shared expert, 40 layers of Gated DeltaNet + gated attention, vision tower, MTP head) on Blackhole through vLLM and the Tenstorrent plugin, with a fused decode step: the…

Runs on
BH 4xP150, BH P300, BH QuietBox 2 +3
Speed
220 tok/s118 ms 4 chips
Status
Not in the release spec
tt launch
7 clients
2 tt-model bundles
LLMCommunity model

Ornith-1.5-9B

ornith-ai/Ornith-1.5-9B

Ornith-1.5-9B, a 9B-parameter dense reasoning and coding model, served with vLLM with tool calling and separated reasoning output.

Runs on
BH 4xP150, p150, p150x2
Speed
6.0 tok/s97 ms 1 chip
Status
Not in the release spec
tt launch
7 clients
1 tt-model bundle
Robotics (inferred)Community model

pi05_base

lerobot/pi05_base

Published as 2 tt-model bundles by changh95.

Runs on
BH QuietBox 2, p150
Status
Not in the release spec
tt launch
None
2 tt-model bundles
Object detectionCommunity model

ptv3

AutowareFoundation/ptv3

Point Transformer V3, a 34.0M-parameter LiDAR network: 0.12 m voxels serialized along two Morton curves, a 5-stage encoder (sparse-conv positional encoding, attention over patches of 512 voxels, grid pooling; about 0.36 TFLOPs on a…

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Image generation (inferred)Community model

Qwen-Image-2.1

Qwen/Qwen-Image-2.1

Published as 1 tt-model bundle by changh95.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Image generation (inferred)Community model

Qwen-Image-Edit_ComfyUI

Comfy-Org/Qwen-Image-Edit_ComfyUI

Published as 1 tt-model bundle by sunandbean.

Runs on
p100a
Status
Not in the release spec
tt launch
None
1 tt-model bundle
LLM (inferred)Community model

Qwen3-Coder-30B-A3B-Instruct

Qwen/Qwen3-Coder-30B-A3B-Instruct

Qwen3-Coder-30B-A3B-Instruct (30B total / 3B active MoE: 128 experts, top-8, 48 layers) for agentic coding with tool calling on Blackhole through vLLM, with a fused MoE decode: the v1 bundle (raahemnabeel/qwen3-coder-30b-a3b-v1) plus the…

Runs on
BH 4xP150, BH P300, BH QuietBox 2 +2
Speed
96 tok/s145 ms 4 chips
Status
Not in the release spec
tt launch
7 clients
1 tt-model bundle
LLM (inferred)Community model

Qwen3-Coder-Next

Qwen/Qwen3-Coder-Next

Qwen3-Coder-Next (80B total / 3B active MoE: 512 experts, top-10 + shared expert, 48 layers of Gated DeltaNet + gated attention) on Blackhole through vLLM and the Tenstorrent plugin, with a fused decode step: the v1 bundle…

Runs on
BH 4xP150, BH P300, BH QuietBox 2 +1
Speed
179 tok/s173 ms 4 chips
Status
Not in the release spec
tt launch
7 clients
1 tt-model bundle
Text-to-speechCommunity model

Qwen3-TTS-12Hz-1.7B-Base

Qwen/Qwen3-TTS-12Hz-1.7B-Base

Qwen3-TTS 1.7B Base, a text-to-speech model that clones the voice of a 3 to 10 s reference clip, in ten languages.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Text-to-speechCommunity model

Qwen3-TTS-12Hz-1.7B-CustomVoice

Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

Qwen3-TTS 1.7B CustomVoice, a text-to-speech model with nine built-in speakers and ten languages.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Text-to-speechCommunity model

Qwen3-TTS-12Hz-1.7B-VoiceDesign

Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign

Qwen3-TTS 1.7B VoiceDesign, a text-to-speech model that speaks in a voice described in a sentence, in ten languages.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
LLM (inferred)Community model

Qwen3.5-122B-A10B

Qwen/Qwen3.5-122B-A10B

Qwen3.5-122B-A10B, a 122B-parameter mixture-of-experts model with 10B parameters active per token (256 experts, top-8 plus a shared expert; 48 layers mixing Gated DeltaNet linear attention with gated full attention) and a vision encoder,…

Runs on
BH 4xP150, BH QuietBox 2
Speed
131 tok/s216 ms 4 chips
Status
Not in the release spec
tt launch
7 clients
1 tt-model bundle
LLM (inferred)Community model

Qwen3.6-35B-A3B

Qwen/Qwen3.6-35B-A3B

Published as 2 tt-model bundles by Adartras, rothgar.

Runs on
BH 4xP150, BH P300, BH QuietBox 2 +2
Status
Not in the release spec
tt launch
7 clients
2 tt-model bundles
LLMCommunity model

Qwen3.8-Flash-Next

Qwen/Qwen3.8-Flash-Next

Qwen3.8-Flash-Next, a mixture-of-experts model with 125B parameters (about 6B active per token) plus a 51B n-gram embedding table, served with vLLM as a text-only chat and completion endpoint with tool calling and separated reasoning…

Runs on
BH 4xP150, BH LoudBox, BH QuietBox 2
Speed
24 tok/s340 ms 4 chips
Status
Not in the release spec
tt launch
7 clients
5 tt-model bundles
Decision model (inferred)Community model

RAG-Gate-27B

ThakiCloud/RAG-Gate-27B

Published as 1 tt-model bundle by episod.

Runs on
p150x2
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Object detection (inferred)Community model

rf-detr-base

Roboflow/rf-detr-base

Published as 1 tt-model bundle by changh95.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Robotics (inferred)Community model

RLDX-1-PT

RLWRLD/RLDX-1-PT

Published as 1 tt-model bundle by changh95.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Robotics (inferred)Community model

RLDX-1-PT-IMG

RLWRLD/RLDX-1-PT-IMG

Published as 1 tt-model bundle by changh95.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Text-to-speechCommunity model

s2-pro

fishaudio/s2-pro

Fish Audio S2 Pro, a 4.5B dual-autoregressive text-to-speech model (Qwen3-based semantic decoder, 400M codebook decoder, 44.1 kHz DAC codec) on Tenstorrent Blackhole, with a fish-speech-compatible /v1/tts API (streaming WAV, voice cloning…

Runs on
BH P300, BH QuietBox 2, p100 +1
Status
Not in the release spec
tt launch
None
2 tt-model bundles
Image segmentation (inferred)Community model

sam3

facebook/sam3

Published as 1 tt-model bundle by changh95.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Image segmentationCommunity model

sceneseg-p150

changh95/sceneseg-p150

SceneSeg, a 48.3M-parameter camera segmentation network (EfficientNet-B0 encoder, a SceneContext block that gates the stride-32 features with a global prior, and a UNet-style decoder of five 2x up-blocks with a 3-class head) on a fixed…

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
LLM (inferred)Community model

SmolLM2-135M-Instruct

HuggingFaceTB/SmolLM2-135M-Instruct

SmolLM2-135M-Instruct, a 135M-parameter Llama-architecture decoder-only transformer, served with vLLM.

Runs on
p100, p150
Status
Not in the release spec
tt launch
2 clients
1 tt-model bundle
LLM (inferred)Community model

Solar-Open-100B

upstage/Solar-Open-100B

Published as 1 tt-model bundle by changh95.

Runs on
BH LoudBox
Status
Not in the release spec
tt launch
7 clients
1 tt-model bundle
Computer vision (inferred)Community model

superpoint

magic-leap-community/superpoint

Published as 1 tt-model bundle by changh95.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Object detectionCommunity model

tensorrt_bevdet

AutowareFoundation/tensorrt_bevdet

BEVDet-R50-4DLongterm-Depth, a 76M-parameter camera-only 3D detector with temporal fusion: a ResNet-50 + FPN image encoder with a camera-aware depth network (118 depth bins) on six cameras at 256x704, a BEVPool v2 lift-splat into a 128 x…

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Object detectionCommunity model

tensorrt_yolox

AutowareFoundation/tensorrt_yolox

YOLOX-s+ seg16, a 15.5M-parameter single-stage camera detector (ELAN CSPDarknet backbone, PAFPN neck, anchor-free decoupled head on strides 8, 16 and 32) with a 16-class semantic-segmentation decoder, run on a 960x960 letterboxed input…

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Depth and 3D geometry (inferred)Community model

VGGT-1B

facebook/VGGT-1B

Published as 1 tt-model bundle by changh95.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle
LLM (inferred)Community model

VibeThinker-3B

WeiboAI/VibeThinker-3B

Published as 1 tt-model bundle by mando2222.

Runs on
p150
Status
Not in the release spec
tt launch
2 clients
1 tt-model bundle
Speech-to-textCommunity model

Voxtral-Mini-4B-Realtime-2602

mistralai/Voxtral-Mini-4B-Realtime-2602

Voxtral-Mini-4B-Realtime-2602, Mistral AI's realtime speech-to-text model (a 970M-parameter causal audio encoder feeding a 3.4B Ministral text decoder; 13 languages; one text token per 80 ms of audio), served on four Blackhole chips (2 x…

Runs on
BH QuietBox 2
Status
Not in the release spec
tt launch
2 clients
1 tt-model bundle
Video generation (inferred)Community model

Wan_2.2_ComfyUI_Repackaged

Comfy-Org/Wan_2.2_ComfyUI_Repackaged

Published as 1 tt-model bundle by sunandbean.

Runs on
p100a
Status
Not in the release spec
tt launch
None
1 tt-model bundle
Robotics (inferred)Community model

xvla-base

lerobot/xvla-base

Published as 1 tt-model bundle by changh95.

Runs on
p150
Status
Not in the release spec
tt launch
None
1 tt-model bundle