Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows

Meta did not abandon opensource. I would love to see a smaller distill, or a moe of this size but the benchmarks seems competetive as long as it isnt benchmaxed witch i would not be suprosed if it is.

Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows

#5

Post by scrlk » Mon, Aug 10, 2026, 10:50 AM UTC

Will be interesting to see how Qwen3.8 27B compares against this once it releases this week. Seems like dense 30B is back in fashion?

EDIT: An open weight version of Muse Spark 1.2 is going to be released as well:

https://x.com/alexandr_wang/status/2086756152034066792

https://xcancel.com/alexandr_wang/status/2086756152034066792

Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows

#6

Post by richardfey » Mon, Aug 10, 2026, 10:51 AM UTC

Looking forward to giving this a try with llama.cpp. I’m watching the open-weights competition with high expectations.

Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows

#7

Post by Gecko4072 » Mon, Aug 10, 2026, 10:52 AM UTC

What I think would be perfect is a model that could run on a single DGX spark and be competitive with DSV4 Flash 731. Flash is already a game changer. Hopefully meta plans on this, like the old 70b. V4 flash is smart enough for any use but slightly too big. 27b-30b isn’t intelligent enough.

Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows

#8

Post by wronglebowski » Mon, Aug 10, 2026, 10:52 AM UTC

scrlk wrote: post #5

Will be interesting to see how Qwen3.8 27B compares against this once it releases this week. Seems like dense 30B is back in fashion? EDIT: An open weight version of Muse Spark 1.2 is going to be released as well: https://x.com/alexandr_wang/status/2086756152034066792 https://xcancel.com/alexandr_wang/status/2086756152034066792

It’s really interesting timing, Qwen over thinking is what kills it for me. I’m just glad we have more options in this size class now.

Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows

#9

Post by InfiniteLoup » Mon, Aug 10, 2026, 10:55 AM UTC

tosh wrote: post #2

good to see new open weights releases from meta

The least they could do, after ruthlessly bombarding my employer's servers with requests, ignoring the robots.txt, scraping everything, and incurring significant Google Maps costs for us in the process.

Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows

#10

Post by sajithdilshan » Mon, Aug 10, 2026, 10:56 AM UTC

Still needs 32-64GB memory to run it locally. 64GB Macbook pro with an M5 chip costs more than 4k Euros in Germany. A more practical model would be a language specific (e.g Python or JVM language) and excellent at tool calling and reasoning. Maybe that way they can shrink it even more.