Downloads · 30 days
13
33% of all-time downloads
K2-V2-Instruct-w8a8-smoothquant
kaitchup/K2-V2-Instruct-w8a8-smoothquant
K2-V2-Instruct-w8a8-smoothquant is a machine learning model from kaitchup. 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 apache-2.0.
This is LLM360/K2-V2-Instruct quantized with LLM Compressor with the recipe in the "recipe.yaml" file. The model is compatible with vLLM (tested: v0.12.0). Tested with an H100.
All-time downloads
39
Public
Parameters
72.6B
84.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors84.9 GB · 100%
Parameter types
How the weights are stored.
I868.5B · 94%
Base models
Model card
From the Hugging Face model README
This is LLM360/K2-V2-Instruct quantized with LLM Compressor with the recipe in the "recipe.yaml" file. The model is compatible with vLLM (tested: v0.12.0). Tested with an H100.
- Developed by: The Kaitchup
- License: Apache 2.0 license
How to Support My Work
Subscribe to The Kaitchup. This helps me a lot to continue quantizing and evaluating models for free. Or you can "buy me a kofi".
- Type
- llama
- License
- apache-2.0
- Created
- Dec 10, 2025
- Updated
- Dec 10, 2025