- Size
- 258M parameterscounted from the safetensors header on the Hub
- Licence
- unknown, Apache License 2.0Our reading, check the licence: You can use, change and redistribute the model, including commercially. Keep the licence and any notices, and say which files you changed; you do not have to publish your changes. It includes a patent licence that ends for anyone who sues over patents in the work.
- On the Hub since
- 19 May 2025the date the repo was created
- Context length
- 8k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)Idefics3ForConditionalGeneration
- On Hugging Face
- ibm-granite/granite-docling-258M415k downloads in the last 30 days, 1.3k likes
Scores
No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.18 GB, worked out from the model's config (ibm-granite/granite-docling-258M), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
ggml-org/granite-docling-258M-GGUF (converted by ggml-org), 2.4k downloads. Sizes are the real files on the Hub, all parts added up. For image input you also need the projector file mmproj-granite-docling-258M-f16.gguf (0.18 GB), not counted below.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q8_0 | 0.17 GBfile size | 0.84 GB0.17 + 0.18 + 0.50 | Commandsllama.cpp llama-server -hf ggml-org/granite-docling-258M-GGUF:Q8_0Ollama ollama run hf.co/ggml-org/granite-docling-258M-GGUF:Q8_0Download hf download ggml-org/granite-docling-258M-GGUF --include "granite-docling-258M-Q8_0.gguf" --local-dir granite-docling-258M-GGUF |
| F16 | 0.31 GBfile size | 0.98 GB0.31 + 0.18 + 0.50 | Commandsllama.cpp llama-server -hf ggml-org/granite-docling-258M-GGUF:F16Ollama ollama run hf.co/ggml-org/granite-docling-258M-GGUF:F16Download hf download ggml-org/granite-docling-258M-GGUF --include "granite-docling-258M-f16.gguf" --local-dir granite-docling-258M-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLXibm-granite/granite-docling-258M-mlx | 0.59 GBfile size | 1.3 GB0.59 + 0.18 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 0.48 GBfile size | 1.2 GB0.48 + 0.18 + 0.50 |
hf download ibm-granite/granite-docling-258M --local-dir granite-docling-258MOther conversions (4; sizes not read)
- onnx-community/granite-docling-258M-ONNX Other, 1.8k downloads
- litert-community/granite-docling-258M Other, 265 downloads
- lamco-development/granite-docling-258M-onnx Other, 25 downloads
- JasonYANG170/granite-docling-258M-ONNX Other, 12 downloads
The Hub tags 16 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.
Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.