meshllm/qwen2.5-0.5b-instruct-parity-8bit-mlx

🤗 Hugging Face sourceapache-2.0494M params988 MBsafetensors✓ 2 checksumsupdated today

Submit in one command

Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo meshllm/qwen2.5-0.5b-instruct-parity-8bit-mlx ./model-folder

Needs a seeder →

Qwen2.5 0.5B Instruct parity MLX (8bit)

This repo contains a same-origin MLX parity artifact derived from Qwen/Qwen2.5-0.5B-Instruct for backend parity testing with mesh-llm.

Validated exact pair:

GGUF: meshllm/qwen2.5-0.5b-instruct-parity-q8_0-gguf
MLX: meshllm/qwen2.5-0.5b-instruct-parity-8bit-mlx

Exact validation result:

GGUF exact: PASS
MLX exact: PASS
prompt-by-prompt outputs matched on the checked-in exact suite used by mesh-llm

Files in this repo are the converted MLX 8bit artifact directory used in validation.