Model reference · open weights
MiniCPM4.1 is an open-weight language model from openbmb, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
👋 Contact us in <a href="https://discord.gg/3cGQn9b3YM" target="blank"Discord</a and <a href="https://github.com/OpenBMB/MiniCPM/blob/main/assets/wechat.jpg" target="blank"WeChat</a What's New - [2025.09.29] InfLLM-V2 paper is released! We can train a sparse attention model with only 5B long-text tokens. 🔥🔥🔥 - [2025.09.05] MiniCPM4.1 series are released! This series is a hybrid reasoning model with trainable sparse attention, which can be used in both deep reasoning mode and non-reasoning mode. 🔥🔥🔥 - [2025.06.06] MiniCPM4 series are released! This model achieves ultimate efficiency improvements while maintaining optimal performance at the same scale! It can achieve over 5x generation acceleration on typical end-side chips! You can find technical report here.🔥🔥🔥 Highlights MiniCPM4.1 is highlighted with following features: ✅ Strong Reasoning Capability: Surpasses similar-sized models on 15 tasks! ✅ Fast Generation: 3x decoding speedup for reasoning! ✅ Efficient Architecture: Trainable sparse attention, frequency-ranked speculative decoding! - MiniCPM4.1-8B: The latest version of MiniCPM4, with 8B parameters, support fusion thinking. (<-- you are here) - MiniCPM4.1-8B-GPTQ: MiniCPM4.1-8B in GPTQ format. - MiniCPM4.1-8B-AutoAWQ: MiniCPM4.1-8B in AutoAWQ format. - MiniCPM-4.1-8B-Marlin: MiniCPM4.1-8B in Marlin format. - MiniCPM4.1-8B-GGUF: MiniCPM4.1-8B in GGUF format. - MiniCPM4.1-8B-MLX: MiniCPM4.1-8B in MLX format. - MiniCPM4.1-8B-Eagle3: Eagle3 model for MiniCPM4.1-8B. - MiniCPM4 Series - MiniCPM4-8B: The flagship model with 8B parameters, trained on 8T tokens - MiniCPM4-0.5B: Lightweight version with 0.5B parameters, trained on 1T tokens - MiniCPM4-8B-Eagle-FRSpec: Eagle head for FRSpec, accelerating speculative inference - MiniCPM4-8B-Eagle-FRSpec-QAT-cpmcu: Eagle head with QAT for FRSpec, integrating speculation and quantization for ultra acceleration - MiniCPM4-8B-Eagle-vLLM: Eagle head in vLLM format for speculative inference - MiniCPM4-8B-marlin-Eagle-vLLM: Quantized Eagle head for vLLM format - BitCPM4-0.5B: Extreme ternary quantization of MiniCPM4-0.5B, achieving 90% bit width reduction - BitCPM4-1B: Extreme ternary quantization of MiniCPM3-1B, achieving
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | openbmb |
|---|---|
| Type | Language models |
| Parameters (lead) | 8.2B |
| Context | 64k tokens |
| Variants | 1 |
| Runs with | transformers |
| Released | 2025-09-02 |
| Popularity | 48k downloads / month |
| Likes | 391 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| MiniCPM4.1-8B | 8.2B | BF16 | ~18.8 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys minicpm4-1 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (minicpm4-1 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"minicpm4-1","messages":[{"role":"user","content":"Hello"}]}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗