Downloads · 30 days
367
6% of all-time downloads
Kimi-Linear-48B-A3B-Instruct-nvfp4
Firworks/Kimi-Linear-48B-A3B-Instruct-nvfp4
Kimi-Linear-48B-A3B-Instruct-nvfp4 is a machine learning model from Firworks. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Format: NVFP4 — weights & activations quantized to FP4 with dual scaling. Base model: moonshotai/Kimi-Linear-48B-A3B-Instruct How it was made: One-shot calibration with LLM Compressor (NVFP4 recipe), long-seq calibrat…
All-time downloads
6.4K
Public
Parameters
28B
28.8 GB on disk
Likes
10
Public
Repo makeup
Click a slice to open those files.
.safetensors28.8 GB · 100%
Parameter types
How the weights are stored.
U824.2B · 86%
Base models
Datasets
Model card
From the Hugging Face model README
Kimi-Linear-48B-A3B-Instruct-nvfp4
Format: NVFP4 — weights & activations quantized to FP4 with dual scaling.
Base model: moonshotai/Kimi-Linear-48B-A3B-Instruct
How it was made: One-shot calibration with LLM Compressor (NVFP4 recipe), long-seq calibration with HuggingFaceH4/ultrachat_200k.
Notes: Keep
lm_headin high precision; calibrate on long, domain-relevant sequences.
Check the original model card for information about this model.
Running the model with VLLM in Docker
sudo docker run --runtime nvidia --gpus all --ipc=host -p 8000:8000 -e VLLM_USE_FLASHINFER_MOE_FP4=1 vllm/vllm-openai:latest Firworks/Kimi-Linear-48B-A3B-Instruct-nvfp4 --served-model-name kimi-48b-nvfp4 --max-model-len 32768 --tensor-parallel-size 2 --trust-remote-code --gpu-memory-utilization 0.7
This was tested on a 2 x RTX Pro 6000 Blackwell cloud instance.
If there are other models you're interested in seeing quantized to NVFP4 for use on the DGX Spark, or other modern Blackwell (or newer) cards let me know. I'm trying to make more NVFP4 models available to allow more people to try them out.
- Type
- kimi_linear
- License
- mit
- Created
- Oct 31, 2025
- Updated
- Nov 27, 2025