CoolFace
Modelpublic

meshllm/lfm2-350m-parity-q4_k_m-gguf

sourceHugging Faceapache-2.0updated 6mo agoView on Hugging Face
0likes20downloads
Model Card

LFM2 350M Parity Q4KM GGUF

Same-origin GGUF artifact for mesh-llm backend comparison.

  • —Source checkpoint: LiquidAI/LFM2-350M
  • —Conversion path: original checkpoint -> GGUF f16 -> GGUF Q4_K_M
  • —Intended pair: meshllm/lfm2-350m-parity-4bit-mlx

Validation

Validated locally with the mesh-llm exact smoke suite on 2026-04-06.

This pair is useful as a backend-drift detector rather than a clean parity canary. In the same-origin exact run, the GGUF side was materially worse than the MLX side on several simple prompts.

Files

  • —lfm2-350m-q4_k_m.gguf