Image-Text-to-Text
Transformers
Safetensors
inkling2
conversational
Mixture of Experts
Eval Results
8-bit precision
modelopt
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
YAML Metadata Error:Invalid content in Eval Result file .eval_results/Inkling-2-Small.yaml
Check out the documentation for more information.
Show details
Task ID "hle" does not match any task in dataset "cais/hle". Available: none
Download .eval_results/Inkling-2-Small.yaml from thinkingmachines/Inkling-2-Small: direct link, hf CLI and curl.
- Browser
- Download file 2.86 kB
-
https://huggingface.co/thinkingmachines/Inkling-2-Small/resolve/main/.eval_results/Inkling-2-Small.yaml
- Command line
-
hf download hf://thinkingmachines/Inkling-2-Small/.eval_results/Inkling-2-Small.yaml
-
curl -L -o Inkling-2-Small.yaml https://huggingface.co/thinkingmachines/Inkling-2-Small/resolve/main/.eval_results/Inkling-2-Small.yaml
2.86 kB
| - dataset: | |
| id: datacurve/deep-swe | |
| task_id: deep_swe | |
| value: 72.1 | |
| date: "2026-11-13" | |
| source: | |
| url: https://huggingface.co/thinkingmachines/Inkling-2-Small | |
| name: "Inkling-2-Small model card" | |
| notes: "DeepSWE v1.1, mini-swe-agent v2.4.6." | |
| - dataset: | |
| id: harborframework/terminal-bench-science | |
| task_id: terminalbenchscience_0_1 | |
| value: 5.7 | |
| date: "2026-11-13" | |
| source: | |
| url: https://huggingface.co/thinkingmachines/Inkling-2-Small | |
| name: "Inkling-2-Small model card" | |
| notes: "mini-swe-agent v2.4.6." | |
| - dataset: | |
| id: ScaleAI/SWE-bench_Pro | |
| task_id: SWE_Bench_Pro_hard | |
| value: 86.3 | |
| date: "2026-11-13" | |
| source: | |
| url: https://huggingface.co/thinkingmachines/Inkling-2-Small | |
| name: "Inkling-2-Small model card" | |
| notes: "mini-swe-agent v2.4.6." | |
| - dataset: | |
| id: likaixin/ScreenSpot-Pro | |
| task_id: overall | |
| value: 83.8 | |
| date: "2026-11-13" | |
| source: | |
| url: https://huggingface.co/thinkingmachines/Inkling-2-Small | |
| name: "Inkling-2-Small model card" | |
| notes: "Images with a long side over 4,096 px downsampled to that limit (aspect ratio kept, ground truth rescaled)." | |
| - dataset: | |
| id: likaixin/ScreenSpot-Pro | |
| task_id: overall | |
| value: 92.0 | |
| date: "2026-11-13" | |
| source: | |
| url: https://huggingface.co/thinkingmachines/Inkling-2-Small | |
| name: "Inkling-2-Small model card" | |
| notes: "With Python tool. Images with a long side over 4,096 px downsampled to that limit (aspect ratio kept, ground truth rescaled)." | |
| - dataset: | |
| id: MMMU/MMMU_Pro | |
| task_id: mmmu_pro_standard_10_options | |
| value: 81.6 | |
| date: "2026-11-13" | |
| source: | |
| url: https://huggingface.co/thinkingmachines/Inkling-2-Small | |
| name: "Inkling-2-Small model card" | |
| - dataset: | |
| id: cais/hle | |
| task_id: hle | |
| value: 44.1 | |
| date: "2026-11-13" | |
| source: | |
| url: https://huggingface.co/thinkingmachines/Inkling-2-Small | |
| name: "Inkling-2-Small model card" | |
| notes: "Text-only subset." | |
| - dataset: | |
| id: Delores-Lin/MDPBench | |
| task_id: overall | |
| value: 81.4 | |
| date: "2026-11-13" | |
| source: | |
| url: https://huggingface.co/thinkingmachines/Inkling-2-Small | |
| name: "Inkling-2-Small model card" | |
| - dataset: | |
| id: ScaleAI/SWE-bench_Pro | |
| task_id: SWE_Bench_Pro | |
| value: 97.7 | |
| date: "2026-11-13" | |
| source: | |
| url: https://thinkingmachines.ai/model-card/inkling-2-small/ | |
| name: "Inkling 2 Small model card (thinkingmachines.ai)" | |
| notes: "SWE-Bench Pro v2 (Full), mini-swe-agent v2.4.6. As reported on the card; higher than the same model's Hard-subset score (86.3), pending confirmation." | |
| - dataset: | |
| id: SWE-bench/SWE-bench_Multimodal | |
| task_id: swe_bench_multimodal_%_resolved | |
| value: 43.1 | |
| date: "2026-11-13" | |
| source: | |
| url: https://thinkingmachines.ai/model-card/inkling-2-small/ | |
| name: "Inkling 2 Small model card (thinkingmachines.ai)" | |
| notes: "SWE-bench Multimodal v2, mini-swe-agent (Vals harness)." | |