fantos/MiniCPM-o-2_6
Any-to-Any • 9B • Updated • 11
master PRO
fantos
AI & ML interests
None yet
Recent Activity
updated a bucket about 3 hours ago
gemma-challenge/gemma-fantos-draft published a bucket about 3 hours ago
gemma-challenge/gemma-fantos-draft reacted to SeaWolf-AI's post with 👍 1 day ago
We wrote up our run in The Fast Gemma Challenge — as vidraft-darwin — and wanted to share the recipe. 🙏
https://huggingface.co/spaces/gemma-challenge/gemma-dashboard
Verified result: 510.58 TPS at PPL 2.3930 on a single A10G (fw188-ctk49-n64-patchbridge, re-run & VERIFIED). Honest note: on raw TPS there are faster runs (535+), but those went over the PPL bar and didn't verify — what we're proud of is the fastest result that keeps quality.
The recipe is already open, so we explained each piece: sliding-window W188, CTK49 kernel tuning, noprecache (honest, verifiable measurement), and an N64 synthetic warmup bridge that shrinks the public↔private gap (~15 TPS), plus INT4 + MTP K=7 + CUDA-graph capture. One rule: only stack quality-neutral speedups.
Huge thanks to @firfir-cast, @gemma-slayer, @chiku-inu, @kenyan-duma, @dixie-flatline and everyone who shared their experiments. Full write-up
👇
https://huggingface.co/blog/FINAL-Bench/fast-gemma
Organizations
fantos/Qwen3-Omni-30B-A3B-Thinking
Any-to-Any • 32B • Updated • 18
fantos/Ming-flash-omni-Preview
Any-to-Any • 104B • Updated • 468
fantos/Qwen-Image-Edit-Rapid-AIO
Text-to-Image • Updated • 1
fantos/GLM-4.6
Text Generation • 357B • Updated • 9
fantos/neutts-air
Text-to-Speech • 0.7B • Updated • 11
fantos/PaddleOCR-VL
Image-Text-to-Text • 1.0B • Updated • 5
fantos/DeepSeek-OCR
Image-Text-to-Text • 3B • Updated • 6
fantos/QwQ-32B-bnb-4bit
Text Generation • 33B • Updated • 7 • 63