zviratko
/

Qwen3.6-27B-Seven-oQ6e-mtp

Model card Files Files and versions

Qwen3.6-27B-Seven-oQ6e-mtp

This model was quantized using oQ (oMLX v0.5.8.dev3) mixed-precision quantization.

Quantization details

Model type: qwen3_5
Bits: 6
Group size: 64
Format: MLX safetensors

Downloads last month: 143

Safetensors

Model size

28B params

Tensor type

U32

·

BF16

·

MLX

Hardware compatibility

Log In to add your hardware

6-bit

Inference Providers NEW

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

Model tree for zviratko/Qwen3.6-27B-Seven-oQ6e-mtp

Base model

Qwen/Qwen3.5-27B

Finetuned

DavidAU/Qwen3.5-27B-Claude-4.6-OS-INSTRUCT

Adapter

nightmedia/Qwen3.6-27B-Seven

Quantized

(3)

this model