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

tosh

good to see new open weights releases from meta

gunalx

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.

scrlk

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

richardfey

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

Gecko4072

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.

sajithdilshan

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.

solarkraft

Wow, Meta is back (at least for now)! I like this class of model. Multi-token prediction makes it viable to run dense models at not-too-far-off speeds as MoE models with much better intelligence. The submission’s title (open weights 30B local coding model) is luckily wrong: This is meant to be a general agentic model. It even comes pre-quantized and with a MTP/drafter model. Looking good! Let’s hope they aren’t dishonest with the benchmarks this time …

Havoc

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

nutjob2

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.

zmmmmm

Meta knows how to win back developer's hearts .... let's see if they have the goods

maxignol

Optimizing speed is really the way to go. Yet 24GB is not what everyone can afford. Maybe we could take some of those 56tk/s and transfer into some free RAM space using MoE loading ? I'd be glad with a less than 10GB and more than 6tk/s model.

bronxbomber92

I wish they would release the quantized versions in a safetensor format. Many frameworks can't load PTE and GGUF.

_ache_

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.

petcat

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 bringing home a dog from the rescue and just hoping that it doesn't have a tendency to bite kids in the face. You just can't know. The only thing that you can do is try to add more training (fine tuning) telling it not to bite kids. I don't think the FOSS community has ever accepted this, but somehow we're feeling like it is okay now.

bentt

Meta seems like the one American bigtech that would distill the the other American frontier models. My enemy’s enemy is my friend?

vibe42

Meta released their own 4-bit quant of this model for devices with 24GB VRAM. That's a modern gaming laptop; cheapest I see in the US with 24GB is $3.5k. Should be quite a bit faster than the new M5 MacBook Pro, and you can run Linux on it!

sgt

Can I run this on my RTX 5090?

polymorph1sm

Some interesting findings from the chat template designs: 1. The template name is Onyx ATEM as found in the tool call exception message 2. It appears to be following a harmony-style chat template. But the tool use seems to be a xml like :<atem:function_calls> / <atem:invoke> / <atem:parameter> 3. atem: a internal joke of meta in reverse? https://huggingface.co/meta-models/Muse-Glimmer-30B/blob/mai...

cmiles8

With the business model for API based LLMs looking iffy at best it seems like we’re heading back to the “server under your desk” era of IT again.

avaer

I lament the comments saying this in any way redeems Meta (the company). The researchers releasing this stuff have almost nothing to do with Meta other than being bankrolled by the slaughterhouse. You aren't the customer, you are the pawn in big tech's game of thrones. Your good will is a commodity to be traded, almost literally. It will be used against you the moment it's convenient. This is open weights because Meta couldn't monetize it in any other way than to cloud developer's judgement of their reputation. But I guess most people just don't care. I'm glad it's open. It does not make me think any better of Meta.