- Size
- 2.5B 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
- 6 Sep 2026the date the repo was created
- Context length
- 128k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)LlamaForCausalLM
- On Hugging Face
- openbmb/MiniCPM5-2B949k downloads in the last 30 days, 1.9k 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: 0.33 GB, worked out from the model's config (openbmb/MiniCPM5-2B), 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
peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF (converted by peculiar-ragdoll), 84k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q4_K_S | 1.4 GBfile size | 2.2 GB1.4 + 0.33 + 0.50 | Commandsllama.cpp llama-server -hf peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF:Q4_K_SOllama ollama run hf.co/peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF:Q4_K_SDownload hf download peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF --include "Sharp-MiniCPM5-2B-Q4_K_S.gguf" --local-dir Sharp-MiniCPM5-2B-GGUF |
| Q4_K_XL | 1.5 GBfile size | 2.3 GB1.5 + 0.33 + 0.50 | Commandsllama.cpp llama-server -hf peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF:Q4_K_XLOllama ollama run hf.co/peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF:Q4_K_XLDownload hf download peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF --include "Sharp-MiniCPM5-2B-Q4_K_XL.gguf" --local-dir Sharp-MiniCPM5-2B-GGUF |
| Q5_K_XL | 1.8 GBfile size | 2.6 GB1.8 + 0.33 + 0.50 | Commandsllama.cpp llama-server -hf peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF:Q5_K_XLOllama ollama run hf.co/peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF:Q5_K_XLDownload hf download peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF --include "Sharp-MiniCPM5-2B-Q5_K_XL.gguf" --local-dir Sharp-MiniCPM5-2B-GGUF |
| Q6_K_XL | 2.0 GBfile size | 2.9 GB2.0 + 0.33 + 0.50 | Commandsllama.cpp llama-server -hf peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF:Q6_K_XLOllama ollama run hf.co/peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF:Q6_K_XLDownload hf download peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF --include "Sharp-MiniCPM5-2B-Q6_K_XL.gguf" --local-dir Sharp-MiniCPM5-2B-GGUF |
| Q8_K_M | 2.7 GBfile size | 3.6 GB2.7 + 0.33 + 0.50 | Commandsllama.cpp llama-server -hf peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF:Q8_K_MOllama ollama run hf.co/peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF:Q8_K_MDownload hf download peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF --include "Sharp-MiniCPM5-2B-Q8_K_M.gguf" --local-dir Sharp-MiniCPM5-2B-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLXopenbmb/MiniCPM5-2B-MLX | 1.3 GBfile size | 2.1 GB1.3 + 0.33 + 0.50 | Download page |
| MLX 4bitmlx-community/MiniCPM5-2B-mlx-4Bit | 1.3 GBfile size | 2.1 GB1.3 + 0.33 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 4.7 GBfile size | 5.5 GB4.7 + 0.33 + 0.50 |
hf download openbmb/MiniCPM5-2B --local-dir MiniCPM5-2BOther conversions (19; sizes not read)
- openbmb/MiniCPM5-2B-GPTQ AWQ, by the maker, 1.0k downloads
- Soulfate24/MiniCPM5-2B-DSpark-Paretrix-GGUF GGUF, 4.7k downloads
- axteam/MiniCPM5-2B-NVFP4A16 NVFP4, 1.8k downloads
- axteam/MiniCPM5-2B-NVFP4 NVFP4, 1.8k downloads
- infosave/MiniCPM5-2B-cmf Other, 1.2k downloads
- Mike0021/MiniCPM5-2B-ONNX Other, 698 downloads
- tixiren/MiniCPM5-2B-ONNX Other, 400 downloads
- mlboydaisuke/MiniCPM5-2B-LiteRT Other, 286 downloads
- axteam/MiniCPM5-2B-FP8-dynamic FP8, 266 downloads
- axteam/MiniCPM5-2B-AWQ-8bit AWQ, 8bit, 261 downloads
- Ttimms/MiniCPM5-2B-NVFP4 GPTQ, nvfp4, 234 downloads
- axteam/MiniCPM5-2B-AWQ-4bit AWQ, 4bit, 199 downloads
- Ttimms/MiniCPM5-2B-FP8 FP8, 141 downloads
- cyankiwi/MiniCPM5-2B-AWQ-INT4 AWQ, int4, 138 downloads
- beyond369/MiniCPM5-2B-EXL3-5.0bpw EXL3, 90 downloads
- Codeflux/MiniCPM5-2B-FP8 FP8, 45 downloads
- AXERA-TECH/MiniCPM5-2B-GPTQ-Int4 GPTQ, int4, 43 downloads
- ewin-reg/MiniCPM5-2B-EXL3-Quantized EXL3, 42 downloads
- sakamakismile/MiniCPM5-2B-NVFP4 GPTQ, nvfp4, 25 downloads
The Hub tags 100 or more 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.