A handbook for your

TT-QuietBox® 2

Hover a path to see what you'll do. Click to dive in.

⚡ Ships with Qwen3-32B pre-loaded — your first token is minutes away, no download.

QB2 Guide Paths — choose your adventure Install Stack tt-smi Run Models First Model Explore Run & build Tinker Customize
Explore
Explore Tenstorrent hardware & software for the first time
6 chapters · 41 min
Enter →
Run & build
Run and build on top of models
6 chapters · 48 min
Enter →
Tinker
Tinker with models and the software & hardware stack
6 chapters · 59 min
Enter →
Customize
Customize your workstation and make it truly your own
5 chapters · 36 min
Enter →
TT-QuietBox 2 — a small-form-factor workstation with a glass side panel showing the liquid-cooled Blackhole cards and teal accent graphics

TT-QuietBox® 2

Blackhole® · 4 chips · liquid-cooled · $9,999

Product page ↗
AI Accelerator
Chips4× Blackhole® (2× p300c cards)
Tensix cores480 total (120 per chip)
AI clock1.35 GHz
SRAM720 MB total (180 MB/chip)
DRAM128 GB GDDR6 total (32 GB/chip)
Bandwidth1,024 GB/s per card
Chip interconnectWarp400 (2× per card, Samtec ARP6)
Host System
CPUAMD Ryzen 7 9700X (8c, 3.8 GHz)
System RAM256 GB DDR5-5600
Storage4 TB NVMe PCIe Gen5
MotherboardASRock B850M-C
OSUbuntu 24.04.3 LTS
PSU1,600 W
Peak draw~1,500 W
Connectivity
Display1× HDMI
USB8× (2× Gen2, 2× Gen1, 4× USB 2.0)
LANGigabit Ethernet
WiFiWi-Fi 6 (802.11ax) dual-band
Bluetooth5.3
Physical
Dimensions9.1 × 17.8 × 15.6 in
Weight20 kg / 44 lbs
CoolingLiquid (38 dBA max)
Operating temp10–35°C (50–95°F)

Source: docs.tenstorrent.com — TT-QuietBox 2 Specifications

What's Running on QB2

Live from the Tenstorrent compatibility matrix — models confirmed or in testing on Quietbox 2 / P150 / P300c hardware.

Updated 2026-07-19 06:00 UTC

Supported Text-to-Image
FLUX.1 [dev]
12B
Flow-matching transformer for photorealistic text-to-image with strong prompt adherence....
tt-inference-server
Supported Text-to-Image
FLUX.1 [schnell]
12B
FLUX distilled to 4 steps — full quality, fraction of the compute. Black Forest Labs, 12B.
tt-inference-server
Supported
meta llama/Llama 3.3 70B Instruct
tt-inference-server
Supported Text-to-Video
Mochi 1
10B
Text-to-video focused on motion quality and temporal coherence. Genmo, 10B.
tt-inference-server
Supported Text-to-Video
Motif Vision 6B Preview
6B
Preview text-to-video from natural language prompts. Motif, 6B.
tt-inference-server
Supported Text-to-Image
SD-XL 1.0-base
6.6B
MMDiT architecture — strong text rendering and prompt control for image generation....
tt-inference-server
Supported Text-to-Speech
SpeechT5 (TTS task)
307M
Mix-transformer segmentation without positional encoding — accurate at low compute....
tt-inference-server
Supported Text-to-Video
Wan2.2
14B
Causal video transformer for text-to-video with strong motion coherence. Alibaba, 14B.
tt-inference-server
Supported
Wan2.2 I2V A14B Diffusers
tt-inference-server
Supported
Z Image Turbo
tt-inference-server
Supported
meta llama/Llama 3.1 8B Instruct
tt-inference-server
Supported
atomic ml ARNOLD Deathmatch Shotgun Rnn
tt-forge
Supported
atomic ml ARNOLD Defend The Center Ff
tt-forge
Supported
atomic ml ARNOLD Health Gathering Ff
tt-forge
Supported
atomic ml ARNOLD Vizdoom 2017 Track1 Rnn
tt-forge
Supported
atomic ml ARNOLD Vizdoom 2017 Track2 Rnn
tt-forge
Supported
cv depth est GLPN KITTI base
tt-forge
Supported
cv depth est MonoDepth2 Mono 1024x320
tt-forge
Supported
cv depth est MonoDepth2 Mono 640x192
tt-forge
Supported
cv depth est MonoDepth2 Mono No Pt 640x192
tt-forge
Supported
cv depth est MonoDepth2 Mono+stereo 1024x320
tt-forge
Supported
cv depth est MonoDepth2 Mono+stereo 640x192
tt-forge
Supported
cv depth est MonoDepth2 Mono+stereo No Pt 640x192
tt-forge
Supported
cv depth est MonoDepth2 Stereo 1024x320
tt-forge
Supported
cv depth est MonoDepth2 Stereo 640x192
tt-forge
Supported
cv depth est MonoDepth2 Stereo No Pt 640x192
tt-forge
Supported
cv image fe MGP STR Base base
tt-forge
Supported
cv image seg SAM Vit Huge
tt-forge
Supported
cv image seg SAM Vit Large
tt-forge
Supported
cv image seg SegFormer B1 Finetuned Ade 512 512
tt-forge
Supported
cv image seg SegFormer B2 Finetuned Ade 512 512
tt-forge
Supported
cv image seg SegFormer B3 Finetuned Ade 512 512
tt-forge
Supported
cv image seg SegFormer B4 Finetuned Ade 512 512
tt-forge
Supported
cv image seg U Net Carvana Unet
tt-forge
Supported
cv image seg U Net carvana unet 480x640
tt-forge
Supported
cv image seg U Net Cityscapes
tt-forge
Supported
cv image seg U Net Segmentation Models PyTorch UNet ResNet101 Backbone
tt-forge
Supported
cv image seg U Net Torchhub Brain Unet
tt-forge
Supported
cv image seg Ultra Fast Lane Detection CULane ResNet18 Backbone
tt-forge
Supported
cv image seg Ultra Fast Lane Detection TuSimple ResNet34 Backbone
tt-forge
Supported
cv image seg Ultra Fast Lane Detection v2 TuSimple ResNet34 Backbone
tt-forge
Supported
cv keypoint det HRNet v2 W18 Osmr
tt-forge
Supported
cv keypoint det HRNet v2 W30 Osmr
tt-forge
Supported
cv keypoint det HRNet v2 W32 Osmr
tt-forge
Supported
cv keypoint det HRNet v2 W40 Osmr
tt-forge
Supported
cv keypoint det HRNet v2 W44 Osmr
tt-forge
Supported
cv keypoint det HRNet v2 W48 Osmr
tt-forge
Supported
cv keypoint det HRNet v2 W64 Osmr
tt-forge
Supported
cv keypoint det HRNet W18
tt-forge
Supported
cv keypoint det HRNet W18 Small
tt-forge
Supported
cv keypoint det HRNet W18 Small v1 Osmr
tt-forge
Supported
cv keypoint det HRNet W18 Small v2
tt-forge
Supported
cv keypoint det HRNet W18 Small v2 Osmr
tt-forge
Supported
cv keypoint det HRNet W18.ms Aug In1k
tt-forge
Supported
cv keypoint det HRNet W30
tt-forge
Supported
cv keypoint det HRNet W32
tt-forge
Supported
cv keypoint det HRNet W40
tt-forge
Supported
cv keypoint det HRNet W44
tt-forge
Supported
cv keypoint det HRNet W48
tt-forge
Supported
cv keypoint det HRNet W64
tt-forge
Supported
cv keypoint det OpenPose base
tt-forge
Supported
distil large v3
tt-inference-server
Supported
mm action prediction OpenVLA OFT Finetuned Libero Goal
tt-forge
Supported
mm action prediction OpenVLA OFT Finetuned Libero Object
tt-forge
Supported
mm action prediction OpenVLA OFT Finetuned Libero Spatial
tt-forge
Supported
mm action prediction OpenVLA OFT openvla oft finetuned libero spatial object goal 10
tt-forge
Supported
mm image text similarity CLIP Base Patch32
tt-forge
Supported
mm image text similarity SigLIP Base Patch16 256
tt-forge
Supported
mm image text similarity SigLIP Base Patch16 256 Multilingual
tt-forge
Supported
mm image text similarity SigLIP Base Patch16 384
tt-forge
Supported
mm image text similarity SigLIP Base Patch16 512
tt-forge
Supported
mm image text similarity SigLIP Large Patch16 256
tt-forge
Supported
mm image ttt Sana 1600M 1024px
tt-forge
Supported
mm image ttt Stable Diffusion UNet Base
tt-forge
Supported
mm tts MusicGen Small base
tt-forge
Supported
mm tts speecht5_vocoder hifigan
tt-forge
Supported
mm tts Stereo Small
tt-forge
Supported
mm visual qa ViLT QA Vqa
tt-forge
Supported
nlp causal lm BLOOM 1b1
tt-forge
Supported
nlp causal lm CodeGen 350M Mono
tt-forge
Supported
nlp causal lm CodeGen 350M Multi
tt-forge
Supported
nlp causal lm CodeGen 350M Nl
tt-forge
Supported
nlp causal lm DeepCogito v1 Preview Llama 3B
tt-forge
Supported
nlp causal lm Falcon 7B Instruct
tt-forge
Supported
nlp causal lm Gemma 2B
tt-forge
Supported
nlp causal lm Gemma 3 1B Instruct
tt-forge
Supported
nlp causal lm Gemma 3 270M Instruct
tt-forge
Supported
nlp causal lm GPT 2 Base
tt-forge
Supported
nlp causal lm GPT 2 Default
tt-forge
Supported
nlp causal lm GPT 2 Large
tt-forge
Supported
nlp causal lm GPT 2 Medium
tt-forge
Supported
nlp causal lm GPT Neo 1 3B
tt-forge
Supported
nlp causal lm GPT Neo 125M
tt-forge
Supported
nlp causal lm GPT Neo 2 7B
tt-forge
Supported
nlp causal lm HuggyLlama Llama 7B
tt-forge
Supported
nlp causal lm Llama 1B Tiny
tt-forge
Supported
nlp causal lm Llama 3.0 8B
tt-forge
Supported
nlp causal lm Llama 3.1 8B
tt-forge
Supported
nlp causal lm Llama 3.2 1B Instruct
tt-forge
Supported
nlp causal lm Llama 3.2 3B Instruct
tt-forge
Supported
nlp causal lm Llama 3B v2
tt-forge
Supported
nlp causal lm Llama Huggyllama 7B
tt-forge
Supported
nlp causal lm Mamba 1.4b HF
tt-forge
Supported
nlp causal lm Mamba 790M HF
tt-forge
Supported
nlp causal lm mamba mamba 790m hf
tt-forge
Supported
nlp causal lm Mistral 7B
tt-forge
Supported
nlp causal lm Mistral Ministral 3B Instruct
tt-forge
Supported
nlp causal lm NanoGPT Default
tt-forge
Supported
nlp causal lm OpenELM 1 1B
tt-forge
Supported
nlp causal lm OpenELM 270M
tt-forge
Supported
nlp causal lm OpenELM 450M
tt-forge
Supported
nlp causal lm OPT 1.3b
tt-forge
Supported
nlp causal lm OPT 125M
tt-forge
Supported
nlp causal lm OPT 350M
tt-forge
Supported
nlp causal lm Phi 2 Phi 2 Pytdml
tt-forge
Supported
nlp causal lm Qwen 1.5 0 5B Chat
tt-forge
Supported
nlp causal lm Qwen 1.5 0.5B
tt-forge
Supported
nlp causal lm Qwen 2.5 0.5B
tt-forge
Supported
nlp causal lm Qwen 2.5 1.5B
tt-forge
Supported
nlp causal lm Qwen 2.5 14B Instruct 1M
tt-forge
Supported
nlp causal lm Qwen 2.5 3B
tt-forge
Supported
nlp causal lm Qwen 2.5 7B Instruct 1M
tt-forge
Supported
nlp causal lm Qwen 2.5 Coder 0.5B
tt-forge
Supported
nlp causal lm Qwen 2.5 Coder 1.5B
tt-forge
Supported
nlp causal lm Qwen 2.5 Coder 1.5B Instruct
tt-forge
Supported
nlp causal lm Qwen 2.5 Coder 3B
tt-forge
Supported
nlp causal lm Qwen 2.5 Coder 3B Instruct
tt-forge
Supported
nlp causal lm Qwen 2.5 Coder 7B Instruct
tt-forge
Supported
nlp causal lm StableLM 3B Alpha
tt-forge
Supported
nlp causal lm StableLM 7B Alpha
tt-forge
Supported
nlp causal lm T5 Base
tt-forge
Supported
nlp causal lm T5 Flan T5 Base
tt-forge
Supported
nlp causal lm T5 Flan T5 Large
tt-forge
Supported
nlp causal lm T5 Flan T5 Small
tt-forge
Supported
nlp causal lm T5 Large
tt-forge
Supported
nlp causal lm T5 Small
tt-forge
Supported
nlp causal lm XGLM 564M
tt-forge
Supported
nlp embed gen BGE 1.5 Large En v1 5
tt-forge
Supported
nlp embed gen Qwen 3 Embedding 0 6B
tt-forge
Supported
nlp masked lm ALBERT Base v1
tt-forge
Supported
nlp masked lm ALBERT Base v2
tt-forge
Supported
nlp masked lm ALBERT Large v1
tt-forge
Supported
nlp masked lm ALBERT Xlarge v2
tt-forge
Supported
nlp masked lm ALBERT Xxlarge v1
tt-forge
Supported
nlp masked lm BERT Base Uncased
tt-forge
Supported
nlp masked lm DistilBERT Base Cased
tt-forge
Supported
nlp masked lm DistilBERT Base Multilingual Cased
tt-forge
Supported
nlp masked lm DistilBERT Base Uncased
tt-forge
Supported
nlp masked lm Perceiver Language Perceiver
tt-forge
Supported
nlp masked lm RoBERTa Xlm Base
tt-forge
Supported
nlp qa ALBERT Squad2
tt-forge
Supported
nlp qa BERT bert large cased whole word masking finetuned squad
tt-forge
Supported
nlp qa BERT Large Finetuned Squad2
tt-forge
Supported
nlp qa DistilBERT Base Cased Distilled Squad
tt-forge
Supported
nlp qa DPR Ctx Encoder Multiset Base
tt-forge
Supported
nlp qa DPR Ctx Encoder Single Nq Base
tt-forge
Supported
nlp qa DPR Question Encoder Multiset Base
tt-forge
Supported
nlp qa DPR Question Encoder Single Nq Base
tt-forge
Supported
nlp qa Gemma 2B
tt-forge
Supported
nlp qa OPT 1.3b
tt-forge
Supported
nlp qa OPT 125M
tt-forge
Supported
nlp qa OPT 350M
tt-forge
Supported
nlp text cls ALBERT Imdb
tt-forge
Supported
nlp text cls BART Large
tt-forge
Supported
nlp text cls BERT Base Uncased Sst 2
tt-forge
Supported
nlp text cls DistilBERT distilbert base uncased finetuned sst 2 english
tt-forge
Supported
nlp text cls GPT Neo 1 3B
tt-forge
Supported
nlp text cls GPT Neo 125M
tt-forge
Supported
nlp text cls GPT Neo 2 7B
tt-forge
Supported
nlp text cls Llama 3 8B
tt-forge
Supported
nlp text cls Llama 3 8B Instruct
tt-forge
Supported
nlp text cls Llama 3.1 8B
tt-forge
Supported
nlp text cls Llama 3.1 8B Instruct
tt-forge
Supported
nlp text cls Llama 3.2 1B
tt-forge
Supported
nlp text cls Llama 3.2 1B Instruct
tt-forge
Supported
nlp text cls Llama 3.2 3B
tt-forge
Supported
nlp text cls Llama 3.2 3B Instruct
tt-forge
Supported
nlp text cls Llama Huggyllama 7B
tt-forge
Supported
nlp text cls OPT 1.3b
tt-forge
Supported
nlp text cls OPT 125M
tt-forge
Supported
nlp text cls OPT 350M
tt-forge
Supported
nlp text cls Phi 1 Phi 1
tt-forge
Supported
nlp text cls Phi 1.5 Phi 1 5
tt-forge
Supported
nlp text cls Phi 2 Phi 2
tt-forge
Supported
nlp text cls Phi 2 Phi 2 Pytdml
tt-forge
Supported
nlp text cls RoBERTa Base Sentiment
tt-forge
Supported
nlp text cls SqueezeBERT Mnli
tt-forge
Supported
nlp token cls ALBERT Base v1
tt-forge
Supported
nlp token cls ALBERT Base v2
tt-forge
Supported
nlp token cls ALBERT Large v1
tt-forge
Supported
nlp token cls ALBERT Xlarge v1
tt-forge
Supported
nlp token cls BERT dbmdz/bert large cased finetuned conll03 english
tt-forge
Supported
nlp token cls DistilBERT Davlan/distilbert base multilingual cased ner hrl
tt-forge
Supported
nlp token cls Phi 1 Phi 1
tt-forge
Supported
nlp token cls Phi 1.5 Phi 1 5
tt-forge
Supported
nlp token cls Phi 2 Phi 2
tt-forge
Supported
nlp token cls Phi 2 Phi 2 Pytdml
tt-forge
Supported
nlp token cls Qwen 2 base
tt-forge
Supported Speech-to-Text
whisper-large-v3
1.5B
99 languages, 680K hours of training audio — built for robust speech recognition. OpenAI,...
tt-inference-server
Supported
yolox_nano
tt-inference-server
Experimental
gemma 4 31b it
tt-inference-server
Experimental Text Generation
gemma-3-27b-it
27B
Largest Gemma 3 — 140-language reasoning, coding, long context. Google, 27B.
tt-inference-server
Experimental
google/gemma 3 27b it
tt-inference-server
Experimental
google/gemma 4 12B it
tt-inference-server
Experimental
google/gemma 4 31B it
tt-inference-server
Experimental
Qwen/Qwen3 32B
tt-inference-server
Experimental
Qwen/Qwen3.6 27B
tt-inference-server
Experimental
Qwen3.6 27B
tt-inference-server
Experimental Text Generation
gemma-3-4b-it
4B
Punches above its weight in reasoning and code. Google, 4B.
tt-inference-server
Experimental
google/gemma 3 4b it
tt-inference-server
Experimental Text Generation
Llama-3.1-8B-Instruct
8B
Multilingual instruction following, tool use, and function calling. Meta, 8B.
tt-inference-server
Experimental
meta llama/Llama 3.2 3B Instruct
tt-inference-server
Experimental
Qwen/Qwen3 4B
tt-inference-server
Experimental
Qwen/Qwen3 8B
tt-inference-server
Experimental
tiiuae/Falcon3 7B Instruct
tt-inference-server