[Model Request]: openbmb/MiniCPM5-1B

Request to add support for this little and efficient model by openbmb: MiniCPM5-1B

Just like Qwen3.5:0.8b or llama3.2:1b, I think this model would run very quickly on edge devices like a laptop. As far as I know it is the best 1b model available right now.

Resources

https://huggingface.co/openbmb/MiniCPM5-1B
Official GGUF quantization available here: https://huggingface.co/openbmb/MiniCPM5-1B-GGUF

Highlights

We are releasing MiniCPM5-1B, the first model in the MiniCPM5 series. It is a dense 1B Transformer built for on-device, local deployment, and resource-constrained scenarios, reaching 1B-class open-source SOTA.

🏆 1B-class open-source SOTA: compared with strong open-source models in the same size class, MiniCPM5-1B reaches SOTA within this comparison set. Its advantage is most visible in agentic tool use, code generation, and difficult reasoning.

🧠 Hybrid Reasoning: built-in <think> chat template, switch via enable_thinking. The same checkpoint serves as both a fast assistant and a deliberate reasoner.

🛠️ Deployment / Fine-tuning Resources: the MiniCPM GitHub repo provides single-page cookbooks and Agent Skills for major inference backends and fine-tuning frameworks.

[...]

Model Information

MiniCPM5-1B has the following features:

• Type: Causal Language Model

• Architecture: Standard LlamaForCausalLM
• Number of Parameters: 1,080,632,832
• Number of Non-Embedding Parameters: 679,552,512
• Number of Layers: 24
• Number of Attention Heads (GQA): 16 for Q and 2 for KV
• Context Length: 131,072

Introduction

MiniCPM5-1B is the first checkpoint in the MiniCPM5 series. It is designed for local assistants, coding agents, tool-use workflows, and reasoning scenarios where a compact model is preferred. The model keeps a small deployment footprint while providing native long-context support and both Think / No Think chat modes through the same checkpoint.

Evaluation Results

We compare MiniCPM5-1B with strong open-source models in the same size class, including LFM2.5-1.2B-Thinking, Qwen3-0.6B/think and Qwen3.5-0.8B/think. These are capable baselines; within this comparison set, MiniCPM5-1B reaches 1B-class open-source SOTA, with its advantage most visible in tool use, code generation, and difficult reasoning. This makes it a practical choice for local coding agents, tool assistants, and reasoning assistants.

Start by reviewing the linked MiniCPM5-1B and MiniCPM5-1B-GGUF resources, then compare the request with existing support for Qwen3.5:0.8b and llama3.2:1b. Done means MiniCPM5-1B is supported and runs correctly on the project’s target devices, including its documented chat modes.