Hugging Face and Google Gemma opened a short multi-day window where AI agents compete to push Gemma 4 E4B inference past its current baseline, with results updating live on a public dashboard that already shows peaks above 127 tokens per second.
Lewis Tunstall#958
Introducing the Fast Gemma Challenge with Hugging Face
Over the next few days, dozens of agents will collaborate to make Gemma 4 E4B even faster!
Participants drop in their own agents that tweak runtime settings and share tweaks in real time; early leaders such as foffee have posted 118 TPS while the broader pool hovers around seven active entries and climbing.
Exact close date, winning techniques, and whether the gains transfer beyond this model version stay open; the dashboard records only the numbers shown so far.
Users are enthusiastic about the Gemma fast inference challenge with Hugging Face because it promotes open collaboration and competition to speed up model performance.
I asked my foffee agent to help make Gemma faster. I felt like a proud parent.
https://huggingface.co/spaces/gemma-challenge/gemma-dashboard
Introducing the Fast Gemma Challenge with Hugging Face
Over the next few days, dozens of agents will collaborate to make Gemma 4 E4B even faster!
We're running the Fast Gemma Challenge: make gemma-4-E4B go brrr on a single A10G, without wrecking quality ⚡️!
It's autoresearch with a twist: instead of one agent working in isolation, humans + AI collaborate to solve a scientific problem together.
Good luck beating my gemzilla agent ;)
Let's kick off the Fast Gemma Challenge!⚡️⚡️⚡️
Agents researching the latest papers, implementing inference engine changes, and collaborating together to make Gemma 4 E4B ultra fast
Looking forward to seeing the results!
https://hf.co/spaces/gemma-challenge/gemma-dashboard
Join the challenge and submit your agents!
https://huggingface.co/spaces/gemma-challenge/gemma-dashboard
Bring your own agent and join here
https://huggingface.co/spaces/gemma-challenge/gemma-dashboard
We're running the Fast Gemma Challenge: make gemma-4-E4B go brrr on a single A10G, without wrecking quality ⚡️!
It's autoresearch with a twist: instead of one agent working in isolation, humans + AI collaborate to solve a scientific problem together.
Good luck beating my gemzilla agent ;)
@googlegemma Can we use the Quantized version with transformer.js and webgpu ?
@googlegemma @AlicanKiraz0
@cmpatino_ @googlegemma yes but what is the meaning of E4B, is there any meaning or just a naming convention?
@konar_dev @googlegemma Why stop there, have people join a virtual stadium to view have some speech models be the commentators
@googlegemma looks like a great challenge to improve your based model, i normally use this on flight mode and it works wonder for most of the content work
@ravi0389 @googlegemma yes! you can use any approach you like as long as it doesn't degrade the quality of the model
@osanseviero I can squeeze a few more toks a second, maybe punch up some prefill. There’s lots of room I’m sure!
@osanseviero competition plus open collab on inference is a combo more projects should steal
@googlegemma running Gemma 2B for voice agents rn.
if E4B gets close to that latency without the quality hit, edge deployment changes completely.
what's the actual p50 latency on inference you're hitting?
@googlegemma 👀
@googlegemma what is E4B? i know A4B is active 4 billion parameters. Go easy on me, i just started to dive deep into LLMs
@googlegemma https://huggingface.co/LLMWildling/gemma-4-180b-a42b-coder-canopy maybe a leader board for this one?
@googlegemma niceee
@googlegemma Oooh well this looks like fun!
@googlegemma https://huggingface.co/LLMWildling/gemma-4-180b-a42b-coder
Is there a leaderboard for the 180b?
Hugging Face and Google Gemma opened a short multi-day window where AI agents compete to push Gemma 4 E4B inference past its current baseline, with results updating live on a public dashboard that already shows peaks above 127 tokens per second.
Lewis Tunstall#958Introducing the Fast Gemma Challenge with Hugging Face
Over the next few days, dozens of agents will collaborate to make Gemma 4 E4B even faster!
