개발자
텐스토렌트 하드웨어에서 모델을 빠르게 가동하고 실행하는 방법을 알아보세요.
두 가지 오픈 소스 SDK를 사용하여 최대한 실물에 가깝게 만들거나, AI 컴파일러에 작업을 맡길 수 있습니다.
모델 지원 테이블
Qwen 3 32B
QuietBox (Wormhole)
LLM
TP=8
QwQ 32B
QuietBox (Wormhole)
LLM
TP=8
DeepSeek R1 Distill Llama 3.3 70B
QuietBox (Wormhole)
LLM
TP=8
Llama 3.1 70B
Galaxy (Wormhole)
LLM
TP=32
Llama 3.1 70B
QuietBox (Wormhole)
LLM
TP=8
Llama 3.1 70B
QuietBox (Blackhole)
LLM
TP=4
Llama 3.2 11B Vision
n300 (Wormhole)
LLM
TP=2
Qwen 2.5 7B
n300 (Wormhole)
LLM
TP=2
Qwen 2.5 72B
QuietBox (Wormhole)
LLM
TP=8
Falcon 7B
n150 (Wormhole)
LLM
Falcon 7B
QuietBox (Wormhole)
LLM
DP=8
Falcon 7B
Galaxy (Wormhole)
LLM
DP=32
Falcon 40B
QuietBox (Wormhole)
LLM
TP=8
Llama 3.1 8B
p100 (Blackhole)
LLM
Llama 3.1 8B
p150 (Blackhole)
LLM
Llama 3.1 8B
2 x p150 (Blackhole)
LLM
DP=2
Llama 3.1 8B
n150 (Wormhole)
LLM
Llama 3.2 1B
n150 (Wormhole)
LLM
Llama 3.2 3B
n150 (Wormhole)
LLM
Mamba 2.8B
n150 (Wormhole)
LLM
Mistral 7B
n150 (Wormhole)
LLM
Mixtral 8x7B
QuietBox (Wormhole)
LLM
TP=8
Whisper (distil-large-v3)
n150 (Wormhole)
Speech-to-Text
Stable Diffusion 1.4
n150 (Wormhole)
Diffusion Model
512 x 512
Stable Diffusion 3.5 Medium
n150 (Wormhole)
Diffusion Model
512 x 512
ResNet-50
n150 (Wormhole)
CNNs and Vision Transformer
(Classification model)
224 x 224
ResNet-50
n300 (Wormhole)
CNNs and Vision Transformer
(Classification model)
224 x 224
DP=2
ResNet-50
QuietBox (Wormhole)
CNNs and Vision Transformer
(Classification model)
224 x 224
DP=8
ResNet-50
Galaxy (Wormhole)
CNNs and Vision Transformer
(Classification model)
224 x 224
DP=32
ViT-base
n150 (Wormhole)
CNNs and Vision Transformer
(Classification model)
224 x 224
ViT-base
n300 (Wormhole)
CNNs and Vision Transformer
(Classification model)
224 x 224
DP=2
ViT-base
QuietBox (Wormhole)
CNNs and Vision Transformer
(Classification model)
224 x 224
DP=8
MobileNet-v2
n150 (Wormhole)
CNNs and Vision Transformer
(Classification model)
224 x 224
YOLOv4
n150 (Wormhole)
CNNs and Vision Transformer
(Object Detection)
320 x 320
YOLOv4
n150 (Wormhole)
CNNs and Vision Transformer
(Object Detection)
640 x 640
YOLOv8x
n150 (Wormhole)
CNNs and Vision Transformer
(Object Detection)
640 x 640
YOLOv8s
n150 (Wormhole)
CNNs and Vision Transformer
(Object Detection)
640 x 640
YOLOv8s_world
n150 (Wormhole)
CNNs and Vision Transformer
(Object Detection)
640 x 640
YOLOv9c
n150 (Wormhole)
CNNs and Vision Transformer
(Object Detection)
640 x 640
YOLOv10x
n150 (Wormhole)
CNNs and Vision Transformer
(Object Detection)
640 x 640
UNet - VGG19
n150 (Wormhole)
CNNs and Vision Transformer
(Segmentation)
256 x 256
SegFormer Semantic Segmentation
n150 (Wormhole)
CNNs and Vision Transformer
(Segmentation)
512 x 512
YOLOv9c
n150 (Wormhole)
CNNs and Vision Transformer
(Segmentation)
640 x 640
UFLD - v2
n150 (Wormhole)
CNNs and Vision Transformer
(Segmentation)
320 x 800
BERT-Large
n150 (Wormhole)
NLP
(Segmentation)
Sentence-Bert (backbone: bert-base)
n150 (Wormhole)
NLP
(Segmentation)
Tenstorrent 시작하기
TT-Forge™
TT-Forge™는 Tenstorrent의 MLIR 기반 컴파일러입니다.
TT-NN™
TT-NN™은 Tenstorrent 하드웨어에서 ML 워크로드를 실행하기 위한 사용자 친화적인 API입니다.
TT-Metalium™
TT-Metalium™은 Tenstorrent의 오픈 소스, 로우 레벨 AI 하드웨어 SDK입니다.
다른 문서를 찾고 계신가요?
예정된 이벤트
Aug 9
COSCUP 2025
Stop by our booth at the Conference for Open Source Coders, Users & Promoters (COSCUP), the largest open source conference in Asia.
Aug 13
Office Hours: TT-Forge
Come learn more about tt-forge, Tenstorrent's AI compiler as we gear up for our public beta. Find out how to access Tenstorrent hardware and share feedback.
교육용 콘텐츠
튜토리얼
튜토리얼
ttnn-visualizer를 설치하고 실행하는 방법을 알아보세요. ttnn-visualizer는 모델을 완벽하게 이해하는 데 도움이 됩니다.
서면 자습서
Bring up LLMs with TTNN
TT-Metalium 스택을 사용하여 Tenstorrent 하드웨어에서 고성능 멀티칩 모델을 불러오는 방법에 대한 안내를 받으세요.
Op Writer's Guide to Dispatch Overhead
이 튜토리얼에서는 디스패치 오버헤드 리소스 할당, 커널 초기화 및 런타임 인수를 최적화하는 다양한 방법을 다룹니다.
