Instructions to use Tiiny/SmallThinker-21BA3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tiiny/SmallThinker-21BA3B-Instruct with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Tiiny/SmallThinker-21BA3B-Instruct")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Tiiny/SmallThinker-21BA3B-Instruct", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Tiiny/SmallThinker-21BA3B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tiiny/SmallThinker-21BA3B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tiiny/SmallThinker-21BA3B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Tiiny/SmallThinker-21BA3B-Instruct

SGLang

How to use Tiiny/SmallThinker-21BA3B-Instruct with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Tiiny/SmallThinker-21BA3B-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tiiny/SmallThinker-21BA3B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Tiiny/SmallThinker-21BA3B-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tiiny/SmallThinker-21BA3B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Tiiny/SmallThinker-21BA3B-Instruct with Docker Model Runner:
```
docker model run hf.co/Tiiny/SmallThinker-21BA3B-Instruct
```

SmallThinker-21BA3B-Instruct

Commit History

Improve model card: Add paper title and abstract

6d471e8
verified

nielsr HF Staff commited on Jul 31, 2025

Improve model card: Add library, paper, GitHub links, and MoE tag (#2)

0ad4904
verified

Yixin Song

nielsr HF Staff commited on Jul 30, 2025

Update README.md

b5bd753
verified

Yixin Song commited on Jul 29, 2025

Update README.md

8c5b3a3
verified

Yixin Song commited on Jul 29, 2025

Update README.md

7883805
verified

Yixin Song commited on Jul 28, 2025

Update README.md

eddd5e2
verified

BLGS commited on Jul 27, 2025

Update README.md

45e4585
verified

BLGS commited on Jul 27, 2025

Update README.md

fe1da60
verified

wdl339 commited on Jul 27, 2025

Update README.md

109a2c4
verified

Yixin Song commited on Jul 27, 2025

Update README.md

eb58b5c
verified

Yixin Song commited on Jul 27, 2025

Update README.md

9b05bde
verified

Yixin Song commited on Jul 27, 2025

Update README.md

b95a223
verified

Yixin Song commited on Jul 27, 2025

Update README.md

eeda259
verified

wdl339 commited on Jul 27, 2025

Update README.md

0c1dea5
verified

wdl339 commited on Jul 27, 2025

Update README.md

3abcff8
verified

wdl339 commited on Jul 27, 2025

Update README.md

d2557f8
verified

wdl339 commited on Jul 27, 2025

Update README.md

e726dc8
verified

yzmizeyu commited on Jul 27, 2025

Update README.md

bcd1a1f
verified

Yixin Song commited on Jul 27, 2025

Update README.md

4859198
verified

Yixin Song commited on Jul 27, 2025

Update README.md

b87c829
verified

Sorrymaker2024 commited on Jul 27, 2025

Update README.md

5f20f2f
verified

Yixin Song commited on Jul 27, 2025

Update README.md

003b904
verified

Yixin Song commited on Jul 27, 2025

Upload model_lm_head.pt with huggingface_hub

92c4144
verified

Yixin Song commited on Jul 27, 2025

Upload model-00003-of-00009.safetensors with huggingface_hub

d7ef047
verified

Sorrymaker2024 commited on Jul 27, 2025

Upload model-00004-of-00009.safetensors with huggingface_hub

9096ac6
verified

Sorrymaker2024 commited on Jul 27, 2025

Upload model-00005-of-00009.safetensors with huggingface_hub

aa89d6f
verified

Sorrymaker2024 commited on Jul 27, 2025

Upload model-00006-of-00009.safetensors with huggingface_hub

787be73
verified

Sorrymaker2024 commited on Jul 27, 2025

Upload model-00007-of-00009.safetensors with huggingface_hub

1d1e6d6
verified

Sorrymaker2024 commited on Jul 27, 2025

Upload model-00008-of-00009.safetensors with huggingface_hub

ef0fb1c
verified

Sorrymaker2024 commited on Jul 27, 2025

Upload model-00009-of-00009.safetensors with huggingface_hub

41e16d0
verified

Sorrymaker2024 commited on Jul 27, 2025

upload weight

c801fda

yixinsong commited on Jul 27, 2025

upload weight

f547afd

yixinsong commited on Jul 27, 2025

minor

bfd2371

yixinsong commited on Jul 27, 2025

upload

e36ff24

yixinsong commited on Jul 27, 2025

minor

ac8cfe2

yixinsong commited on Jul 26, 2025

upload config

1040800

yixinsong commited on Jul 26, 2025

initial commit

3bfc484
verified

Yixin Song commited on Jul 26, 2025

Commit History

Improve model card: Add paper title and abstract 6d471e8 verified

Improve model card: Add library, paper, GitHub links, and MoE tag (#2) 0ad4904 verified

Update README.md b5bd753 verified

Update README.md 8c5b3a3 verified

Update README.md 7883805 verified

Update README.md eddd5e2 verified

Update README.md 45e4585 verified

Update README.md fe1da60 verified

Update README.md 109a2c4 verified

Update README.md eb58b5c verified

Update README.md 9b05bde verified

Update README.md b95a223 verified

Update README.md eeda259 verified

Update README.md 0c1dea5 verified

Update README.md 3abcff8 verified

Update README.md d2557f8 verified

Update README.md e726dc8 verified

Update README.md bcd1a1f verified

Update README.md 4859198 verified

Update README.md b87c829 verified

Update README.md 5f20f2f verified

Update README.md 003b904 verified

Upload model_lm_head.pt with huggingface_hub 92c4144 verified

Upload model-00003-of-00009.safetensors with huggingface_hub d7ef047 verified

Upload model-00004-of-00009.safetensors with huggingface_hub 9096ac6 verified

Upload model-00005-of-00009.safetensors with huggingface_hub aa89d6f verified

Upload model-00006-of-00009.safetensors with huggingface_hub 787be73 verified

Upload model-00007-of-00009.safetensors with huggingface_hub 1d1e6d6 verified

Upload model-00008-of-00009.safetensors with huggingface_hub ef0fb1c verified

Upload model-00009-of-00009.safetensors with huggingface_hub 41e16d0 verified

upload weight c801fda

upload weight f547afd

minor bfd2371

upload e36ff24

minor ac8cfe2

upload config 1040800

initial commit 3bfc484 verified

Improve model card: Add paper title and abstract

6d471e8
verified

Improve model card: Add library, paper, GitHub links, and MoE tag (#2)

0ad4904
verified

Update README.md

b5bd753
verified

Update README.md

8c5b3a3
verified

Update README.md

7883805
verified

Update README.md

eddd5e2
verified

Update README.md

45e4585
verified

Update README.md

fe1da60
verified

Update README.md

109a2c4
verified

Update README.md

eb58b5c
verified

Update README.md

9b05bde
verified

Update README.md

b95a223
verified

Update README.md

eeda259
verified

Update README.md

0c1dea5
verified

Update README.md

3abcff8
verified

Update README.md

d2557f8
verified

Update README.md

e726dc8
verified

Update README.md

bcd1a1f
verified

Update README.md

4859198
verified

Update README.md

b87c829
verified

Update README.md

5f20f2f
verified

Update README.md

003b904
verified

Upload model_lm_head.pt with huggingface_hub

92c4144
verified

Upload model-00003-of-00009.safetensors with huggingface_hub

d7ef047
verified

Upload model-00004-of-00009.safetensors with huggingface_hub

9096ac6
verified

Upload model-00005-of-00009.safetensors with huggingface_hub

aa89d6f
verified

Upload model-00006-of-00009.safetensors with huggingface_hub

787be73
verified

Upload model-00007-of-00009.safetensors with huggingface_hub

1d1e6d6
verified

Upload model-00008-of-00009.safetensors with huggingface_hub

ef0fb1c
verified

Upload model-00009-of-00009.safetensors with huggingface_hub

41e16d0
verified

upload weight

c801fda

upload weight

f547afd

minor

bfd2371

upload

e36ff24

minor

ac8cfe2

upload config

1040800

initial commit

3bfc484
verified