X · Min Choi·· 1 天前AI 评分74
Meta 发布 Muse Spark Open，NVIDIA 推出 Nemotron 3.5 Bolt
Open weights had a huge day. Meta released Muse Spark Open. 816B parameters. 42B active. 1M token context. Meta calls it the most capable US open-weight model to date. NVIDIA dropped Nemotron 3.5 Bolt: the 120B Super VL compressed to 74B (9B active) and squeezed into 24GB. #1 on PinchBench among models of its size, and it's open. Frontier-level models you can run yourself are getting closer every week.
AI 导读
Meta 发布开源权重模型 Muse Spark Open，816B 参数、42B 激活、1M token 上下文，Meta 称其为迄今最强的美国开源权重模型。同日 NVIDIA 发布 Nemotron 3.5 Bolt，将 120B Super VL 压缩到 74B（9B 激活）并塞进 24GB，在同尺寸模型中位列 PinchBench 第一且开源。
博主
Min Choi@minchoi
粉丝 39万
Building with Super Intelligence. Sharing what's wild, what's practical, and what's next.
互动数据
- 浏览
- 1.3万
- 点赞
- 43
- 评论
- 23
- 分享
- 8
- 收藏
- 10
约为这个来源平时的 1.9 倍
数字来自平台，为最近一次抓取时的数据。
来源：X · Min Choi · x.com