caiovicentino1/Qwopus3.5-9B-v3-PolarQuant-Q5
Text Generation • 9B • Updated • 2.37k • 8
HLWQ Unified (Weights Q5 + KV Cache Q3)
Full-stack HLWQ: Q5 weights + torchao INT4 + Q3 KV cache · formerly PolarQuant Unified
-
-
caiovicentino1/Qwen3.5-9B-Claude-Opus-PolarQuant-Q5
Text Generation • 9B • Updated • 1.54k • 3 -
caiovicentino1/Qwen3.5-27B-Claude-Opus-PolarQuant-Q5
Text Generation • 27B • Updated • 1.82k -
caiovicentino1/Qwopus3.5-9B-v3-PolarQuant-MLX-4bit
Text Generation • 1B • Updated • 1.58k • 6 -
caiovicentino1/Qwen3.5-9B-PolarQuant-Q5
Text Generation • 9B • Updated • 1.5k • 3 -
caiovicentino1/Qwen3.5-9B-PolarQuant-MLX-4bit
Text Generation • 1B • Updated • 1.96k • 3 -
caiovicentino1/Nemotron-Cascade-2-30B-A3B-PolarQuant-Q5
Text Generation • 20B • Updated • 2.36k • 7 -
caiovicentino1/Gemma-4-31B-it-PolarQuant-Q5
Text Generation • Updated • 1.31k • 4 -
caiovicentino1/Gemma-4-31B-it-PolarQuant-Q5-Vision
Image-Text-to-Text • Updated • 240 • 6 -
caiovicentino1/Gemma-4-26B-A4B-it-PolarQuant-Q5
Image-Text-to-Text • 27B • Updated • 264 • 5 -
caiovicentino1/Gemma-4-31B-Claude-Opus-PolarQuant-Q5-Vision
Image-Text-to-Text • Updated • 496 • 17 -
caiovicentino1/Qwopus3.5-27B-v3-PolarQuant-Q5
Text Generation • Updated • 2.29k • 16 -
caiovicentino1/Qwen3.5-9B-Neo-PolarQuant-Q5
Text Generation • Updated • 1.04k • 4 -
caiovicentino1/Gemma-4-E4B-it-PolarQuant-Multi
Any-to-Any • Updated • 255 • 2 -
caiovicentino1/HY-OmniWeaving-PolarQuant-Q5
Text-to-Video • Updated • 6
caiovicentino1/Gemopus-4-26B-A4B-it-HLWQ-Q5
Image-Text-to-Text • UpdatedNote HLWQ Q5 · 16.6 GB · 27B Gemma-4 26B-A4B MoE · per-expert, consumer GPU ready
caiovicentino1/MiniMax-M2.7-HLWQ-Q5
Text Generation • Updated • 1Note Full-stack HLWQ on MiniMax-M2.7 229B MoE