essigpeng
/

Qwen3-235B-A22B-Instruct-2507-MOE-MXFP4-GGUF

Text Generation

Model card Files Files and versions

(Non-pure) quantized version of: Qwen/Qwen3-235B-A22B-Instruct-2507, using llama-quantize for MXFP4_MOE.

Downloads last month: 72

GGUF

Model size

235B params

Architecture

qwen3moe

Hardware compatibility

Log In to view the estimation

We're not able to determine the quantization variants.

View all variants

Model tree for essigpeng/Qwen3-235B-A22B-Instruct-2507-MOE-MXFP4-GGUF

Base model

Qwen/Qwen3-235B-A22B-Instruct-2507

Quantized

(54)

this model