Compressed versions of Google Gemma4
👋 Open to Work
Vladimir Bashin
voves
AI & ML interests
Lead LLMOps
Recent Activity
updated a model about 2 hours ago
voves/Qwen3.8-27B-NVFP4 published a model about 2 hours ago
voves/Qwen3.8-27B-NVFP4 new activity 2 days ago
RadixArk/Qwen3.8-27B-DSpark:[BUG] DSpark slower than EAGLE + severe cold-start penaltyOrganizations
models 6
voves/Qwen3.8-27B-NVFP4
Image-Text-to-Text • 27B • Updated • 1
voves/gemma-4-26B-A4B-it-NVFP4
Image-Text-to-Text • 26B • Updated • 28
voves/gemma-4-26B-A4B-it-FP8
Image-Text-to-Text • 26B • Updated • 38
voves/GigaChat3.5-432B-A28B-NVFP4
Text Generation • 243B • Updated • 101 • 1
voves/Mellum2-12B-A2.5B-Instruct-FP8
Text Generation • 12B • Updated • 103
voves/Mellum2-12B-A2.5B-Thinking-FP8
Text Generation • 12B • Updated • 10
datasets 0
None public yet