Skip to content

jasperg662

gpt-oss-120b-mxfp4-fp8attn-v2

jasperg662/gpt-oss-120b-mxfp4-fp8attn-v2

gpt-oss-120b-mxfp4-fp8attn-v2 is a machine learning model from jasperg662. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.

This checkpoint was created by grafting FP8 attention weights into the MXFP4 model. Unlike v1 (llmcompressor), this uses a two-step process:

Downloads · 30 days

24

13% of all-time downloads

All-time downloads

183

Public

Parameters

120B

64.3 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors64.3 GB · 100%

Parameter types

How the weights are stored.

U8118B · 98%

Base models

Type
gpt_oss
License
other
Created
Feb 23, 2026
Updated
Feb 23, 2026