MiniCPM5 2B SFT
MiniCPM5 2B SFT is a dense 2B-parameter Transformer text-generation model from the MiniCPM5 series, released under the Apache 2.0 license. According to its official model card, it is built for on-device, local deployment and resource-constrained scenarios, and supports English and Chinese. The model card describes strengths in coding, mathematics, long-context understanding, tool use and agentic tasks, and positions it as 2B-class open-source SOTA while remaining competitive with 4B-class models overall. It is associated with the transformers library, safetensors format, and a set of UltraData and Ultra series datasets.
At a glance
- Parameters
- 2.52B
- Architecture
- llama
- Context length
- 131,072
- License
- apache-2.0
- Software
- llama.cpp, SGLang, vLLM
Will it run on your machine?
Save your machine to see a personalized rating and its reasoning.
Add my hardwareBest for
- Text generation with Transformers for local or on-device deployment
- English and Chinese language tasks
- Long-context understanding tasks
- Tool-calling and agentic workflows
- Coding and mathematics tasks
Tradeoffs
- Model card provides no explicit context-length value, memory requirement, latency figure, or throughput benchmark
- Compatibility, hardware requirements, and performance are not specified in the supplied facts
- The card states SOTA and comparison claims without independent verification
- No safety, bias, or toxicity evaluation is provided
- License and deployment details beyond the stated Apache-2.0 license are not supplied
Ways to run it
llama.cpp · Windows, macOS, Linux
Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.
llama-server -m MiniCPM5-2B-F16.gguf -a MiniCPM5-2B --port 8080 -ngl 99 -c 8192 --jinjaSGLang · Linux
Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.
python -m sglang.launch_server --model-path openbmb/MiniCPM5-2B --port 30000vLLM · Linux
Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.
vllm serve openbmb/MiniCPM5-2B --port 8000Explore its uses
Keep exploring
Bonsai 2 · 27B
A compressed 27B-class reasoning model with publisher-provided GGUF packs and a dedicated llama.cpp fork for CUDA, Metal, and CPU.
DeepSeek V4.1 Flash
A multimodal reasoning model with a compressed key-value cache, published as open weights.
Qwen3.8-Flash-Next
An experimental open-weight multimodal model with sparse attention and 262K native context.