MiniCPM-o-4_5
Runs on your machine
Choose a machine
We then show the largest format that fits, from real file sizes where we have them.
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: 1.1 GB, worked out from the model's config (openbmb/MiniCPM-o-4_5), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
weights context cache runtime
GGUF for llama.cpp, Ollama, LM Studio and others
openbmb/MiniCPM-o-4_5-gguf (the maker's own conversion), 129k downloads. Sizes are the real files on the Hub, all parts added up. Showing the common levels.
| Format | Size | Memory needed | Memory | Get it |
|---|---|---|---|---|
| Q4_K_M | 4.7 GBfile size | 6.3 GB4.7 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf openbmb/MiniCPM-o-4_5-gguf:Q4_K_MOllama ollama run hf.co/openbmb/MiniCPM-o-4_5-gguf:Q4_K_MDownload hf download openbmb/MiniCPM-o-4_5-gguf --include "MiniCPM-o-4_5-Q4_K_M.gguf" --local-dir MiniCPM-o-4_5-gguf | |
| Q5_K_M | 5.4 GBfile size | 7.1 GB5.4 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf openbmb/MiniCPM-o-4_5-gguf:Q5_K_MOllama ollama run hf.co/openbmb/MiniCPM-o-4_5-gguf:Q5_K_MDownload hf download openbmb/MiniCPM-o-4_5-gguf --include "MiniCPM-o-4_5-Q5_K_M.gguf" --local-dir MiniCPM-o-4_5-gguf | |
| Q6_K | 6.3 GBfile size | 7.9 GB6.3 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf openbmb/MiniCPM-o-4_5-gguf:Q6_KOllama ollama run hf.co/openbmb/MiniCPM-o-4_5-gguf:Q6_KDownload hf download openbmb/MiniCPM-o-4_5-gguf --include "MiniCPM-o-4_5-Q6_K.gguf" --local-dir MiniCPM-o-4_5-gguf | |
| Q8_0 | 8.1 GBfile size | 9.7 GB8.1 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf openbmb/MiniCPM-o-4_5-gguf:Q8_0Ollama ollama run hf.co/openbmb/MiniCPM-o-4_5-gguf:Q8_0Download hf download openbmb/MiniCPM-o-4_5-gguf --include "MiniCPM-o-4_5-Q8_0.gguf" --local-dir MiniCPM-o-4_5-gguf |
MLX for Apple silicon
| Format | Size | Memory needed | Memory | Repo |
|---|---|---|---|---|
| MLX 4bitandrevp/MiniCPM-o-4_5-MLX-4bit | 6.5 GBfile size | 8.1 GB6.5 + 1.1 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Memory | Repo |
|---|---|---|---|---|
| BF16original weights | 17.5 GBfile size | 19.1 GB17.5 + 1.1 + 0.50 |
hf download openbmb/MiniCPM-o-4_5 --local-dir MiniCPM-o-4_5Other conversions (6; sizes not read)
- openbmb/MiniCPM-o-4_5-awq AWQ, by the maker, 15k downloads
- openbmb/MiniCPM-o-4_5-GPTQ GPTQ, by the maker, 244 downloads
- axteam/MiniCPM-o-4_5-FP8-dynamic FP8, 302 downloads
- ericleigh007/MiniCPM-o-4_5-BNB-Int4 bitsandbytes, int4, 91 downloads
- ericleigh007/MiniCPM-o-4_5-BNB-Int8 bitsandbytes, int8, 22 downloads
- Edith08/MiniCPM-o-4_5-q4 Other, 13 downloads
The Hub tags 13 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, 15:16 UTC. The repo. Found a mistake on this page? Tell us.