Qwen3.8-27B 4-bit MLX

MLX conversion of Qwen/Qwen3.8-27B, quantized with mlx-lm 0.31.3 using affine 4-bit weights and group size 64 (4.501 effective bits per weight). The safetensors weights occupy approximately 14 GB.

Comparative quality and performance benchmarks are not available for this conversion.

Use with mlx

from mlx_lm import load, generate

model, tokenizer = load("DreamFoundries/Qwen3.8-27B-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)

---