Instructions to use thinkingmachines/Inkling-2-Small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use thinkingmachines/Inkling-2-Small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="thinkingmachines/Inkling-2-Small") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("thinkingmachines/Inkling-2-Small") model = AutoModelForMultimodalLM.from_pretrained("thinkingmachines/Inkling-2-Small", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Inference
- HuggingChat
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use thinkingmachines/Inkling-2-Small with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "thinkingmachines/Inkling-2-Small" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "thinkingmachines/Inkling-2-Small", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/thinkingmachines/Inkling-2-Small
- SGLang
How to use thinkingmachines/Inkling-2-Small 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 "thinkingmachines/Inkling-2-Small" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "thinkingmachines/Inkling-2-Small", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'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 "thinkingmachines/Inkling-2-Small" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "thinkingmachines/Inkling-2-Small", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use thinkingmachines/Inkling-2-Small with Docker Model Runner:
docker model run hf.co/thinkingmachines/Inkling-2-Small
Add minimal quantization config to correct Hub parameter count
Summary
Add the minimal top-level quantization metadata in config.json so the Hub reports approximately 594.05B parameters.
+ "quantization_config": {
+ "quant_method": "modelopt",
+ "quant_algo": "NVFP4"
+ }
The Hub's ModelOpt counting rules exclude *_weight_scale tensors and count two FP4 values per packed U8 weight. F8_E4M3 experts in layers 40–47 remain one value per element. This is the minimal counting config; the existing hf_quant_config.json still describes the NVFP4/MXFP8 mix.
Evidence
Ran computeNumOfParamsByDtypeSingleFile from @huggingface/hub@2.17.10 against the real safetensors headers of all 24 shards, pinned to aac974122acd33ddb0d3e1f54433a9c5dd2249ce. No weight payloads were downloaded.
- Before:
383,072,987,216parameters; exactly matches the current Hub count. - After:
594,050,672,720parameters (594.05B).
The explicit 48-layer MIXED_PRECISION config produces the same count.
Checked that the JSON is valid and this block is the only semantic change.
Merge Danger
Door: two-way — remove this block to revert.
Blast Radius: config
This validates Hub parameter counting only. Transformers/vLLM inference loading has not been validated. The current Transformers auto-quantizer registry does not register modelopt; maintainers should confirm the Inkling2 loading path accepts this metadata before merging.
Thank you!