Chubby♨️@kimmonismus
57AI 编辑部评分,满分 100
2026-08-10 19:12· 18分钟前
AI 导读

Meta 回归开源,其 30B 参数模型 Muse Glimmer 在 24 项基准中 12 项取得最佳成绩,并在 19 项上超越 Gemma4-31B、14 项超越 Qwen3.6-27B。该模型主打智能体能力,4-bit 量化版仅约 17GB,性能损失约 1%。权重将以 Apache 2.0 协议完全开放,Spark 1.2 权重也将很快发布。

I'm genuinely happy that Meta is back in the open-source game.

The weights for Spark 1.2 will be released soon as well!

I just wish they had kept the name Llama.

Chubby♨️LFG: Meta's Muse Glimmer is a remarkably capable model for its size: 30B parameters, local deployment, and the best reported result on 12 of 24 benchmark rows a...

来源:Chubby♨️ · x.com

Chubby♨️ · @kimmonismus · X·2026-08-10 19:12·18分钟前
AI 导读

Meta 回归开源,其 30B 参数模型 Muse Glimmer 在 24 项基准中 12 项取得最佳成绩,并在 19 项上超越 Gemma4-31B、14 项超越 Qwen3.6-27B。该模型主打智能体能力,4-bit 量化版仅约 17GB,性能损失约 1%。权重将以 Apache 2.0 协议完全开放,Spark 1.2 权重也将很快发布。

I'm genuinely happy that Meta is back in the open-source game.

The weights for Spark 1.2 will be released soon as well!

I just wish they had kept the name Llama.

Chubby♨️LFG: Meta's Muse Glimmer is a remarkably capable model for its size: 30B parameters, local deployment, and the best reported result on 12 of 24 benchmark rows a...

来源:Chubby♨️· x.com