You can deploy this model and start earning money today!

augible/
qwen3.5-2b-4bit-text-mlx

Name: qwen3.5-2b-4bit-text-mlx
Availability: InStock

Views

No views yet

Qwen3.5-2B — 4-bit MLX, text-only layout

The text decoder of Qwen/Qwen3.5-2B (Apache-2.0), quantized to 4-bit with mlx-lm (group 64, affine) and re-keyed to the qwen3_5_text layout (model.* tree) so mlx-swift-lm's Qwen35TextModel + PEFT adapter loader consume it directly. The chat template is pinned to non-thinking rendering. Base weights only — no fine-tuning of any kind.

augible/qwen3.5-2b-4bit-text-mlx

Qwen3.5-2B — 4-bit MLX, text-only layout

augible/
qwen3.5-2b-4bit-text-mlx