⚡️ Gemma 4 31B Turbo is now the #3 trending quant on HuggingFace. Just 24h after release. Didn't expect this 🤯 Thanks to everyone who downloaded and shared. Really. --- What did you ship with 2.5× faster Gemma 4 31B? 👇 https://twitter.com/LilaRest/status/2042641828269146572/photo/1
中文: ⚡️ Gemma 4 31B Turbo 现已成为 HuggingFace 上第三大热门量子。 发布后仅24小时。没想到会这样🤯 感谢所有下载并分享的人。真的。 - 你用2.5倍快的Gemma 4 31B发货了什么?👇
Introducing 𝐆𝐞𝐦𝐦𝐚 𝟒 𝟑𝟏𝐁 𝐓𝐮𝐫𝐛𝐨 ⚡️ It runs on a 𝘴𝘪𝘯𝘨𝘭𝘦 RTX 5090, at 51 tok/s (single) and 1244 tok/s (batched). And prefills up to 15359 tok/s. It's 𝟔𝟖% 𝐬𝐦𝐚𝐥𝐥𝐞𝐫 in GPU memory and ~𝟐.𝟓𝐱 𝐟𝐚𝐬𝐭𝐞𝐫 than the base model, and retains nearly… https://twitter.com/LilaRest/status/2042320271005069618/photo/1
中文: 推出 Gemma 4 31B Turbo ⚡️ 它采用单次RTX 5090,单次运行,单次运行为51 tok/s,并采用1244 tok/s(单次单次)运行。预填充时间高达15359。 GPU内存小68%,比基础型号快约2.5倍,且几乎保持在...