Qwopus3.6-27B-v2 MLX 4bit-gs32

Higher-quality 4-bit, tighter group size.

MLX conversion of Jackrong/Qwopus3.6-27B-v2.

Use

pip install mlx-lm
mlx_lm.generate --model zaydiscold/Qwopus3.6-27B-v2-MLX-4bit-gs32 \
  --prompt "Explain quantum entanglement" --max-tokens 200 --temp 0.8

Author's temperature recommendation: 0.75–1.0.

The MLX ladder

Variant	Repo
bf16	`Qwopus3.6-27B-v2-MLX-bf16`
4bit	`Qwopus3.6-27B-v2-MLX-4bit`
4bit-gs32 (this repo)	this

Credits

Source: Jackrong/Qwopus3.6-27B-v2 by Jackrong
MLX conversion by zaydiscold

Mix brought by the NOTORIOUS MLX.

Downloads last month: 9

Safetensors

Model size

28B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for zaydiscold/Qwopus3.6-27B-v2-MLX-4bit-gs32

Base model

Jackrong/Qwopus3.6-27B-v2

Quantized

(59)

this model

Collection including zaydiscold/Qwopus3.6-27B-v2-MLX-4bit-gs32

Qwopus3.6-27B-v2 MLX

Collection

MLX quant suite of Jackrong/Qwopus3.6-27B-v2 for Apple Silicon. Mix brought by the NOTORIOUS MLX. • 16 items • Updated May 23