any improvements that can be done the cheapest A100?
🤝 Open to Collab
Marcin Sadowski
gitsad
AI & ML interests
Gen UI
Recent Activity
repliedto danielhanchen's post 1 day ago
We’re releasing Gemma 4 NVFP4 quants that run 1.5× faster on your GPU.
Gemma-4-12B NVFP4 works on 11GB VRAM.
26B-A4B hits 13K tok/s (B200).
Unsloth NVFP4 enables faster, more accurate 4-bit Blackwell inference.
Blog: https://unsloth.ai/docs/basics/nvfp4
Gemma NVFP4: https://huggingface.co/collections/unsloth/nvfp4 updated a model 16 days ago
MobileReality/mdma-gemma4-26b-dsl-unsloth-v1 published a model 16 days ago
MobileReality/mdma-gemma4-26b-dsl-unsloth-v1Organizations
replied to danielhanchen's post 1 day ago
updated a
model 16 days ago
published a
model 16 days ago