kaitchup
/

Olmo-3.1-32B-Instruct-MXFP4

8-bit precision

compressed-tensors

Model card Files Files and versions

Experimental. Doesn't run with vLLM v0.13.

Downloads last month: 8

Safetensors

Model size

18B params

Tensor type

BF16

·

U8

·

Inference Providers NEW

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