llmixer
/

Qwen3-235B-A22B-4.0bpw-h6-exl3

Text Generation

4-bit precision

Model card Files Files and versions

4.0 bpw exl3 quant of Qwen/Qwen3-235B-A22B

Runs on 5x24GB with 16k context (Q6).

Downloads last month: 2

Safetensors

Model size

60B params

Tensor type

F16

·

I16

·