Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

research.meta.ai

Post reply on HN
Print view View original

71–80 of 682 posts

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

#71

Post by neuroticnews25 »

dbbk wrote: post #58
sajithdilshan wrote: post #10

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.

Well if you're spending thousands on API tokens already, you could just drop the same amount on a 128GB MacBook Pro and that's a one time cost.

Don't forget about energy usage, you'll probably never break even vs same model on openrouter.

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

#72

Post by smallerize »

dbbk wrote: post #58
sajithdilshan wrote: post #10

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.

Well if you're spending thousands on API tokens already, you could just drop the same amount on a 128GB MacBook Pro and that's a one time cost.

If you're dropping thousands on API tokens, you're going to be slowed down at least 10x trying to do everything on a single MBP.

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

#73

Post by echelon »

mycall wrote: post #64
pu_pe wrote: post #46

Earlier quoted context omitted.

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.

Do AI companies make release plans based on upcoming other models like this? I would think all the processes that go into the repository and weight infrastructure pre-training, checkpointing, knowledge distillation, model compression, post training pipeline, ecosystem integrations, inference API, benchmarking, human eval/safety/alignment, docs, etc... all that dictates the release schedule.

There has been a long history of AI model releases made shortly before or after a major planned release by another company. Almost always to upstage or steal thunder.

Just recently, Minimax H3 released as open weights on the eve of Seedance 2.5 global availability. It's not as good, but it's good enough and it's completely open.

Flux 3, which is nowhere near as good as either, suddenly announced their release once news of these other two became public. They knew if they waited they'd be ignored. It didn't really help them much, unfortunately.

The LLM releases are even more rivalrous.

And don't forget all of the competing launches planned before Google IO or major release events.

Companies like to eat into the news and press cycle of their rivals.

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

#74

Post by imilev »

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

yes i think everyone is waiting to see that ;d, i've been on qwen for the last year and a half now.

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

#75

Post by mapontosevenths »

Manfrednotfunny wrote: post #25
Gecko4072 wrote: post #15

Earlier quoted context omitted.

There have been discussions on language specific not really being a relevant change to reduce size.

I would love to see any good research projects about it but i have the feeling that Frontier with MoE is making too fast of a progress so that a customized model would always be worse and that the MoE part is actually going somehow in this direction. On the other hand, at the GTC was a talk about coding in different lanugage (like spanish) and explaining that the quality between spanish and english is relevant differ…

Capability in LLM's is distributed throughout the manifold in subspaces. Even worse, the subspaces exist in superposition.

That is to say, there is no single 'python' part of the model. The python bit is spread throughout the entire model and overlaps with other pieces that have similar, but unrelated, capabilities. For example the python subpspace might be partially in superposition with cupcake recipes, Esperanto, and calculus. We need calculus in a coding agent but not the other two. However, separating them cleanly is almost impossible, and even identifying them is tough.

Internally the manifolds are highly inefficient and nothing like you would imagine something humans built would be designed. It's more like something that evolved in nature.

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

#76

Post by zamalek »

formerly_proven wrote: post #60
sajithdilshan wrote: post #10

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.

4K bucks buys you around 180 months of with zero upfront cost.

Problem is that might go away or get nerfed.

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

#77

Post by OtherShrezzing »

cynicalsecurity wrote: post #69
sajithdilshan wrote: post #10

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.

I don't understand the desire to run own AI models for programming locally. No laptop is ever going to be as powerful and energy efficient to run anything close to OpenAI, Anthropic or Google models. A model you can run on a loptop is simply not going to work as well as it's needed for programming. Small models for linguistic work fine, but anything more sophisticated simply won't provide enough resources or power. O…

> A model you can run on a loptop is simply not going to work as well as it's needed for programming

The models you can run on a high-spec laptop today are approximately where frontier models were 12-18mo ago (albeit at a lower tok/s rate). If you scan back through hn comments from that era, you’ll find plenty of people saying “this is powerful enough to massively increase my productivity”.

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

#79

Post by ComputerPerson »

cynicalsecurity wrote: post #69
sajithdilshan wrote: post #10

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.

I don't understand the desire to run own AI models for programming locally. No laptop is ever going to be as powerful and energy efficient to run anything close to OpenAI, Anthropic or Google models. A model you can run on a loptop is simply not going to work as well as it's needed for programming. Small models for linguistic work fine, but anything more sophisticated simply won't provide enough resources or power. O…

I've never done it but would be interested because it cuts out the burden of worrying about costs. Maybe I'm mistaken on energy cost here. There's a constant raincloud that follows me around regarding limits, and it would be nice to shake that.

I've been able to accomplish incredible feats (for myself) since GPT-4, so model intelligence is secondary.

Post reply on HN