Downloads · 30 days
17
22% of all-time downloads
MiniCPM5-1B-NVFP4-W4A4
MaxDevv/MiniCPM5-1B-NVFP4-W4A4
MiniCPM5-1B-NVFP4-W4A4 is a machine learning model from MaxDevv. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
NVFP4 (W4A4) quantized version of openbmb/MiniCPM5-1B.
All-time downloads
79
Public
Parameters
1.1B
1.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.2 GB · 99%
Parameter types
How the weights are stored.
U8679M · 63%
Model card
From the Hugging Face model README
MiniCPM5-1B-NVFP4-W4A4
NVFP4 (W4A4) quantized version of openbmb/MiniCPM5-1B.
Quantized with llm-compressor
using the NVFP4 scheme, saved in compressed-tensors format. Both weights and
activations are FP4 (W4A4): per-group-16 static fp8 weight scales, and per-group
local dynamic fp8 activation scales (static_minmax observer).
Calibration: 128 samples drawn from the
canada-quant/hy3-w4a16-mtp-calibration
blend (code / math / chat, ~2048 tokens each), formatted through this model's
chat template. lm_head is left in bf16.
Loadable directly in vLLM. Needs a Blackwell GPU with CUDA 13 (e.g. RTX 5090) for native FP4 kernels:
vllm serve MaxDevv/MiniCPM5-1B-NVFP4-W4A4 \
--kv-cache-dtype fp8_e4m3 \
--attention-backend flashinfer
Original model below:
- Type
- llama
- Created
- Aug 8, 2026
- Updated
- Aug 8, 2026