hugpadhugpad

nerkyor / Qwen3.5-4B-GGUF-imatrix

Text Generation961Updated May 24, 2026
Hugging Face

Downloads

96

Likes

1

Last updated

May 24, 2026

License

apache-2.0

This repository ships an imatrix-calibrated Q4KM GGUF of the official Qwen/Qwen3.5-4B BF16 weights, built on DGX Spark (GB10, sm121) by the Lynn team.

Tasks & library

  • text generation
  • gguf

Tags

  • gguf
  • qwen3.5
  • q4_k_m
  • imatrix
  • llama.cpp
  • lynn

Technical specifications

ParametersNot available
Librarygguf
Languageszh, en
Base modelQwen/Qwen3.5-4B
Licenseapache-2.0