plawanrath/phi-3.5-mini-instruct-q3-mlx-cba
Text Generation • 0.5B • Updated • 82
Quantization Undoes Alignment — IEEE Cloud Summit 2026
MLX artifacts for the IEEE Cloud Summit 2026 paper. 3 LLMs × 5 precisions (BF16/Q8/Q6/Q4/Q3, gs=64).
-
-
plawanrath/phi-3.5-mini-instruct-q4-mlx-cba
Text Generation • 0.6B • Updated • 50 -
plawanrath/phi-3.5-mini-instruct-q6-mlx-cba
Text Generation • 0.8B • Updated • 22 -
plawanrath/mistral-7b-instruct-v0.3-q3-mlx-cba
Text Generation • 0.9B • Updated • 66 -
plawanrath/qwen2.5-7b-instruct-q3-mlx-cba
Text Generation • 1.0B • Updated • 25 -
plawanrath/mistral-7b-instruct-v0.3-q4-mlx-cba
Text Generation • 1B • Updated • 33 -
plawanrath/phi-3.5-mini-instruct-q8-mlx-cba
Text Generation • 1B • Updated • 27 -
plawanrath/qwen2.5-7b-instruct-q4-mlx-cba
Text Generation • 1B • Updated • 13 -
plawanrath/mistral-7b-instruct-v0.3-q6-mlx-cba
Text Generation • 7B • Updated • 18 -
plawanrath/qwen2.5-7b-instruct-q6-mlx-cba
Text Generation • 8B • Updated • 12 -
plawanrath/phi-3.5-mini-instruct-bf16-mlx-cba
Text Generation • 4B • Updated • 23 -
plawanrath/mistral-7b-instruct-v0.3-q8-mlx-cba
Text Generation • 7B • Updated • 29 -
plawanrath/qwen2.5-7b-instruct-q8-mlx-cba
Text Generation • 8B • Updated • 19 -
plawanrath/mistral-7b-instruct-v0.3-bf16-mlx-cba
Text Generation • 7B • Updated • 12 -
plawanrath/qwen2.5-7b-instruct-bf16-mlx-cba
Text Generation • 8B • Updated • 10