| license: apache-2.0 | |
| base_model: Qwen/Qwen3-8B | |
| tags: | |
| - mesh-llm | |
| - gguf | |
| - qwen3 | |
| - parity | |
| # Qwen3 8B parity GGUF (Q8_0) | |
| Same-origin GGUF parity artifact for `Qwen/Qwen3-8B`, produced for backend comparison work in `mesh-llm`. | |
| - Source checkpoint: `Qwen/Qwen3-8B` | |
| - Conversion flow: original checkpoint -> GGUF f16 -> GGUF Q8_0 | |
| - Intended pair: `meshllm/qwen3-8b-parity-8bit-mlx` | |
| This repo is for backend-parity testing rather than for claiming best overall model quality. | |