Attn: Q4_K

Experts: IQ2_S

Please refer to unsloth for running this model.

./llama.cpp/llama-quantize --imatrix /work/yanzhi_group/models/unsloth/Qwen3-235B-A22B-GGUF/imatrix_unsloth.dat --keep-split /work/yanzhi_group/models/unsloth/Qwen3-235B-A22B-GGUF/BF16/Qwen3-235B-A22B-BF16-00001-of-00010.gguf /scratch/xie.yany/Qwen/Qwen3-235B-A22B-IQ2_S/Qwen3-235B-A22B-IQ2_S.gguf IQ2_S

Downloads last month: 55

GGUF

Model size

235B params

Architecture

qwen3moe

Hardware compatibility

2-bit

Inference Providers NEW

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

Model tree for tflsxyy/Qwen3-235B-A22B-IQ2_S

Base model

Qwen/Qwen3-235B-A22B

Quantized

(13)

this model