Ultra Quantization Hybrid Model.
Collection
These models are quantized in mixed precision that allows them to have a smaller footprint than fp8, but still high quality. • 13 items • Updated
• 1
Rocky Lynn Stein PRO
rockylynnstein
AI & ML interests
IBM Granite, coding and law.
Recent Activity
new activity
24 days ago
TevunahAi/Nemotron-3-Nano-30B-A3B-GPTQ:SGLang Deployment Compatibility for Agentic Workloads new activity
24 days ago
TevunahAi/Nemotron-3-Nano-30B-A3B-GPTQ:Add mlx conversion updated
a collection
about 2 months ago
Ultra Quantization Hybrid Model. Organizations
SGLang Deployment Compatibility for Agentic Workloads
1
#1 opened about 2 months ago
by
yalmasri
Add mlx conversion
1
#2 opened 26 days ago
by
alejandroblancorevolut
updated a collection about 2 months ago
updated a model about 2 months ago
published a model about 2 months ago
updated a model about 2 months ago
updated a collection about 2 months ago
updated a model about 2 months ago
published 2 models about 2 months ago
updated a model about 2 months ago
published a model about 2 months ago
updated a model about 2 months ago
published a model about 2 months ago
updated a model about 2 months ago
published a model about 2 months ago