Models

BH 4xP150

Device keys in tt-inference-server: P150X4.

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.

30 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
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

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-3.3-70B-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

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
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
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
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
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
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
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
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
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
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