Hacker News new | past | comments | ask | show | jobs | submit
_ache_ | on: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows
It is interesting but it does look like a careful distillation of (Spark and) biggers open-weight models.

The progress compared to Qwen3.6 27B is good, not that impressive, it's a 4 months old model. (kuto to them to compare to 27B dense and not 35B MoE, it's more fair to do so). It is very probable that Qwen3.8 27B will crush Glimmer-30B on most benchmarks.

skohan | parent | next
Still great if they want to play in this space. Having competition for the 24-32GB VRAM target is only good for the end user.
drob518 | root | parent
Agreed, the trend in this consumer-accessible range is encouraging.
pettijohn | parent
I'm so excited about these two new models. Qwen 3.6 27B has been my sweet spot so I cannot wait to try 3.8. Glimmer looks really strong, I'm encouraged that Meta compared it to 3.6 in the model card! Exciting times!