jamesdumay's picture
Add files using upload-large-folder tool
1a2502c verified
metadata
license: apache-2.0
base_model: Qwen/Qwen3-0.6B
tags:
  - mesh-llm
  - gguf
  - qwen3
  - parity

Qwen3 0.6B parity GGUF (Q8_0)

Same-origin GGUF parity artifact for Qwen/Qwen3-0.6B, produced for backend comparison work in mesh-llm.

  • Source checkpoint: Qwen/Qwen3-0.6B
  • Conversion flow: original checkpoint -> GGUF f16 -> GGUF Q8_0
  • Intended pair: meshllm/qwen3-0.6b-parity-8bit-mlx

This repo is for backend-parity testing rather than for claiming best overall model quality.