Based on Unsloth's GGUF.

Real world test

I asked LLM (quantized in IQ1_S_M) to summerize the recently published DeepSeekMathV2 paper.

Screenshot from 2025-11-28 11-14-27

Screenshot from 2025-11-28 11-14-33

Screenshot from 2025-11-28 11-14-38

Screenshot from 2025-11-28 11-14-42

Screenshot from 2025-11-28 11-14-50

Downloads last month
352
GGUF
Model size
235B params
Architecture
qwen3vlmoe
Hardware compatibility
Log In to view the estimation

1-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for lovedheart/Qwen3-VL-235B-A22B-Instruct-GGUF

Quantized
(19)
this model