MLX 6-bit conversion of
OpenBMB/MiniCPM5-2B
, a 2B dense Llama-based model for local deployment, coding, reasoning, long-context work, and tool use. The source checkpoint supports a native context length of
131,072 tokens (128K)
.
Benchmarks
Benchmark results reported by OpenBMB for the original MiniCPM5-2B checkpoint.
Release
Format
Quantization
Size
MLX safetensors
Affine 6-bit, group size 64
2.0 GB
The model is text-only. No vision projector or MTP files are included.
MiniCPM5-2B-MLX-6bit huggingface.co is an AI model on huggingface.co that provides MiniCPM5-2B-MLX-6bit's model effect (), which can be used instantly with this abenzerps MiniCPM5-2B-MLX-6bit model. huggingface.co supports a free trial of the MiniCPM5-2B-MLX-6bit model, and also provides paid use of the MiniCPM5-2B-MLX-6bit. Support call MiniCPM5-2B-MLX-6bit model through api, including Node.js, Python, http.
MiniCPM5-2B-MLX-6bit huggingface.co is an online trial and call api platform, which integrates MiniCPM5-2B-MLX-6bit's modeling effects, including api services, and provides a free online trial of MiniCPM5-2B-MLX-6bit, you can try MiniCPM5-2B-MLX-6bit online for free by clicking the link below.
abenzerps MiniCPM5-2B-MLX-6bit online free url in huggingface.co:
MiniCPM5-2B-MLX-6bit is an open source model from GitHub that offers a free installation service, and any user can find MiniCPM5-2B-MLX-6bit on GitHub to install. At the same time, huggingface.co provides the effect of MiniCPM5-2B-MLX-6bit install, users can directly use MiniCPM5-2B-MLX-6bit installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
MiniCPM5-2B-MLX-6bit install url in huggingface.co: