kind of a nonspecific complaint, but i haven’t yet had much luck with anything under ~120b, feels like models released on that order is coming to a trickle. the last few qwen models didn’t seem to go that high, and i got worse results than qwen3.5-122b
Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows
511–520 of 682 posts
Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows
#512Earlier quoted context omitted.
> Are you, for example, wishing for the demise of the United States? Do you want to tear down the 1st Amendment and the Statue of Liberty? Are you against democracy? Do you want our businesses and factories to shut down and go out of business? Are you willing or would you support foreign countries attacking our military at home and abroad? Are you cheering against our athletes? I am very pro the "dream" of America, i…
> I am very pro the "dream" of America, in terms of liberty, democracy, etc. According to every "democracy index" I'm aware of we're not doing so hot in that regard, generally rating as a flawed/deficient democracy and the trends are going in the wrong direction, fast. Well, to be fair people do have different dreams. I'm not sure those indices count for a whole lot. As an example, folks who argue in favor of returni…
To answer most of the questions above simultaneously (to some degree):
I only care about the content of someone's character and how their actions impact the rest of the world, not the country they happen to be a citizen of, a fact which for non-immigrants (the vast majority of people) is completely random happenstance.
If already wealthy foreign agents become wealthier at the expense of impoverished Americans, I find that to be unfortunate. If already wealthy Americans become wealthier at the expense of impoverished non-Americans, I find that to be just as unfortunate.
I'm not going to cheer someone (athlete, business leader, or otherwise) on just because they are American. The fact that they are American is as irrelevant to me as the color of their eyes.
Do they seem to be a good person who treats others well? If yes, I will cheer for that person, whether they are American or not. Do they seem like an entitled asshole that treats others poorly? If yes, I will cheer against that person, whether they are American or not.
And the reason I currently label myself anti-America is that I believe that collectively we are the entitled asshole that treats others poorly. And we can't just pawn that off on Trump to be the scapegoat. He didn't materialize out of nowhere. We elected him. Twice. The second time after a failed insurrection. We have collective culpability.
Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows
#513Earlier quoted context omitted.
We've barely even started on optimizations like advanced language aware grammars, and specialization routing (dynamically loading fine tunes or seperate weights for specific tasks or languages).
Right. But those still sound like modest gain territory, or qualitative gains within the same rough performance, rather than the "breakthrough" improvement notion I was responding to. My naïve impression is that the LLM world will keep delivering these fractional improvements for some years at the cost of simplicity. And sure, ontological support seems quite promising. But making things radically better or faster for…
The gains wouldn't be "free lunch", it's the result of time and effort researching optimal design and architecture.
Even if the idea of "no free lunch" was taken liberally discounting the cost of research, it would only be limiting to systems built from a foundation of optimization, but that's not the case. The foundation so far has been one of brute force scaling. Usually meaning there is lots of room for optimization.
Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows
#514The combo that makes agents reliable: progressive tool routing, persistent memory, and multi-model failover.
Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows
#515Earlier quoted context omitted.
Right. But those still sound like modest gain territory, or qualitative gains within the same rough performance, rather than the "breakthrough" improvement notion I was responding to. My naïve impression is that the LLM world will keep delivering these fractional improvements for some years at the cost of simplicity. And sure, ontological support seems quite promising. But making things radically better or faster for…
The gains wouldn't be "free lunch", it's the result of time and effort researching optimal design and architecture. Even if the idea of "no free lunch" was taken liberally discounting the cost of research, it would only be limiting to systems built from a foundation of optimization, but that's not the case. The foundation so far has been one of brute force scaling. Usually meaning there is lots of room for optimizati…
> The foundation so far has been one of brute force scaling.
In cloud AI, sure. But in the smaller open weights model territory it feels like we're well into optimisation?
Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows
#516Earlier quoted context omitted.
Yes, and also waiting for the next iteration of Gemma. Muse or Qwen are optimized for coding, while IMO Gemma is still better for non-coding tasks. https://x.com/osanseviero/status/2086107547535122767
I am working on a project where we have to classify customer calls into more than 10 categories. As the client wants everything locally I tried a few local LLMs. Gemma turned out to be the best model for this task. The classification accuracy is impressive, and the client is happy that I am using an American model.
I guess the client is American.
Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows
#517Earlier quoted context omitted.
When you say you are anti-American, what do you mean by that? Are you, for example, wishing for the demise of the United States? Do you want to tear down the 1st Amendment and the Statue of Liberty? Are you against democracy? Do you want our businesses and factories to shut down and go out of business? Are you willing or would you support foreign countries attacking our military at home and abroad? Are you cheering a…
Why would you tear down a gift from France?
Well I certainly wouldn't, but it's a cultural symbol of America and so when you think anti-American I'd think things like tearing down the symbols that represent our nation would probably be in play. Maybe not, idk. That's why I mentioned it and asked.
Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows
#518In my experience it's faster (10tk/s vs 35tk/s) and better than qwen3.6 series.
Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows
#519Will 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
Based on the benchmarks, it seems that Muse Glimmer barely edges out against Qwen3.6 27B, except for tool-calling skills (MCP, etc.). I wouldn't be surprised if they released it now because they are afraid they wouldn't beat Qwen3.8 27B.
I would hope that Qwen 3.8 is better. It's been 4 months, and we've seen almost no progress in this space.
As people have called out, Glimmer appears to be a trade-off rather than a clear winner.
And from what I've been reading, no one is expecting Qwen 3.8's model in this space to be a clear winner, but just slightly and marginally better.
That's a little concerning as DeepSeek v4 Flash proved at it larger sizes there's a ton of room left to compress knowledge.
If we don't see something that's substantially better in the ~30B param space soon - it would appear we might've saturated that size with knowledge.
Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows
#520Remember when we needed 200 servers for an enterprise website because Apache used one process or thread per connection - and Nginx collapsed that into a single box overnight? That moment for LLMs is near. It’s going to move us from the big iron era of AI to small portable brains. Nature has already proved it’s possible with 20 watts and very little heat generation. And I think the data center buildout will end in car…
What does this have to do with Muse Glimmer 30B?