FP8 quants - a marksverdhei Collection

marksverdhei 's Collections

Qwen3 Voice Embedding

Currently using

FP8 quants

updated Jan 20

A collection of my FP8 quants for models missing this.

marksverdhei/GLM-4.7-Flash-FP8

Text Generation • Updated 27 days ago • 99.5k • 18
marksverdhei/Qwen3-Omni-30B-A3B-FP8

Any-to-Any • 35B • Updated Jan 20 • 4k • 2