useful-quants/Gemma-4-26B-A4B-it-W4A16-G64-BF16Vision
Image-Text-to-Text • 26B • Updated • 133 • 1
Useful Quants
community
AI & ML interests
Practical quantized model repackagings for local inference, focused on fast, tested, hardware-friendly variants for real homelab workloads.
Recent Activity
View all activity
models 13
useful-quants/LFM2.5-VL-3B-NVFP4-FP8-MinVRAM
Image-Text-to-Text • 2B • Updated • 41 • 1
useful-quants/LFM2.5-VL-3B-NVFP4-FP8-Mixed
Image-Text-to-Text • 2B • Updated • 1.98k • 1
useful-quants/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-W4A16
Text Generation • 32B • Updated • 26.3k • 3
useful-quants/FastContext-1.0-4B-RL-w4a16-g128
Text Generation • 4B • Updated • 103
useful-quants/GLM-4.6V-Flash-W4A16-BF16Vision
Image-Text-to-Text • 10B • Updated • 35 • 2
useful-quants/Ministral-3-3B-Instruct-2512-W4A16-BF16Vision
Text Generation • 4B • Updated • 61
useful-quants/Qwen3-VL-4B-Instruct-W4A16-BF16Vision
Image-Text-to-Text • 4B • Updated • 18
useful-quants/Qwen3-4B-Instruct-2507-W4A16-G128
Text Generation • 4B • Updated • 24
useful-quants/InternVL3-5-8B-W4A16-INT4
Image-Text-to-Text • 3B • Updated • 19
datasets 0
None public yet