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

51–60 of 682 posts

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

#51

Post by microtonal »

petcat wrote: post #49

As an industry, I wish we would stop calling these things "open weight" because it is too easy to confuse with actual "open source", which they are not. Photoshop source code+ OSI license = open source Photoshop binary you can run on your own computer = open weight Photoshop SaaS web app = closed, proprietary (Opus, GPT, etc.) "Open weight" models are still just binary blobs that are completely inscrutable. It's like…

Photoshop source code+ OSI license = open source

Photoshop binary you can run on your own computer = open weight

I don't think this is a correct analogy. You are not allowed to distribute modified versions of the Photoshop binary. Most open weight model licenses allow you to make and distribute your own finetunes, etc.

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

#52

Post by monster_truck »

petcat wrote: post #49

As an industry, I wish we would stop calling these things "open weight" because it is too easy to confuse with actual "open source", which they are not. Photoshop source code+ OSI license = open source Photoshop binary you can run on your own computer = open weight Photoshop SaaS web app = closed, proprietary (Opus, GPT, etc.) "Open weight" models are still just binary blobs that are completely inscrutable. It's like…

This analogy is terrible and seems to be extremely misinformed about how rescues evaluate dogs before they are put up for adoption

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

#53

Post by petu »

cmrdporcupine wrote: post #38
Havoc wrote: post #13

The favourable comparisons to Gemma 4 and qwen3.6 look promising!

Those two offer MoE variants, this doesn't seem to. Dense model makes it dog slow on anything without HBM. Max 15tok/sec on decode on DDR5 systems like a Spark or a Strix Halo -- and that's at 4 bit quant.

3090/4090 probably would do 40 t/s, for 5090 75 t/s is shown in the blog.

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

#54

Post by petcat »

monster_truck wrote: post #52
petcat wrote: post #49

As an industry, I wish we would stop calling these things "open weight" because it is too easy to confuse with actual "open source", which they are not. Photoshop source code+ OSI license = open source Photoshop binary you can run on your own computer = open weight Photoshop SaaS web app = closed, proprietary (Opus, GPT, etc.) "Open weight" models are still just binary blobs that are completely inscrutable. It's like…

This analogy is terrible and seems to be extremely misinformed about how rescues evaluate dogs before they are put up for adoption

I am extremely well aware of how rescues evaluate dogs. And I'm also fully aware that they do not know the full history of the dog. They go through a limited set of testing and interrogation to evaluate the safety of the dog. That's it.

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

#55

Post by mihaelm »

ishtanbul wrote: post #29
mihaelm wrote: post #26

Earlier quoted context omitted.

I'm sooo happy I pulled the trigger on upgrading and getting a new laptop (with 64 GB RAM) last summer. Feels like it was just in time before the exponential price jumps.

Pulled the trigger?

lol, you're right, the brainfart completely changes the meaning.

I corrected it.

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

#56

Post by cmrdporcupine »

nutjob2 wrote: post #14

The more open weight models get released the greater the market for personal and small business oriented hardware to run these models. This will drive lower cost hardware, which has stagnated in recent years due to most software not needing the performance and capacity.

The opposite happening because foundries are full to capacity making higher margin stuff.

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

#57

Post by QuadmasterXLII »

petcat wrote: post #49

As an industry, I wish we would stop calling these things "open weight" because it is too easy to confuse with actual "open source", which they are not. Photoshop source code+ OSI license = open source Photoshop binary you can run on your own computer = open weight Photoshop SaaS web app = closed, proprietary (Opus, GPT, etc.) "Open weight" models are still just binary blobs that are completely inscrutable. It's like…

Given an open weights model trained to sometimes bite kids, we can’t train it to not bite kids, even though billions of dollars of research have been thrown at this open problem.

Given an open weights model trained to never bite kids, you can get it to bite kids with 10 prompts and a linear projection, the known simple algorithm doesn’t even need a backwards pass.

yay asymmetry!

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

#58

Post by dbbk »

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.

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

#59

Post by IsTom »

lostmsu wrote: post #32
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 seems worse than 3.6, but a bit smaller. UPD. was wrong on smaller, it's actually much larger

How is 30B smaller than 27B?

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

#60

Post by formerly_proven »

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.
Post reply on HN