LocalClaw/LLM/Muse Glimmer 30B
Open-weight local LLM

Muse Glimmer 30B

Catalogue summary: Meta Superintelligence Lab local agent model with text+image input, 131K context, Apache 2.0 weights and official GGUF/ExecuTorch artifacts. The K-Quant 17GB build targets 24GB machines; 32GB is safer for vision and long-context sessions.

Repository editorial metadata; verify comparative claims in the linked upstream material.

24 GB catalogue minimum24 GB RAMK-Quant 17GB Q4_K_MCoding assistant
Choose an app

Pick the app you already use. No terminal and no command to copy.

Compare models
Open in LM StudioOpens the app on this model's download screenOpen in UnslothLaunches Unsloth Desktop on this model's download page
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloadsOpen llama.cpp setupAdvanced option: opens the model filesUse with LocalClawOptional workspace after the model is installed

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Parameters
29.8B multimodal
Minimum RAM
24 GB
Model size
17 GB
Quantization
K-Quant 17GB Q4_K_M

Can Muse Glimmer 30B run locally?

Muse Glimmer 30B has a catalogue minimum of 24 GB RAM with K-Quant 17GB Q4_K_M. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Use muse-glimmer-30b as the catalogue search term in a compatible runtime, and confirm the available format on the upstream repository before download.

Model sourcePublic GGUF repository (verified 2026-09-07): meta-models/Muse-Glimmer-30B-GGUFUpstream releasePaper or model cardLicence text
chatcodereasoningagenticvisionlong-contextpowerquality

Install path

01
Check RAM fitMinimum 24 GB RAM. Start with the K-Quant 17GB Q4_K_M quant.
02
Load the modelSearch muse-glimmer-30b in LM Studio.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Catalogue record

  • Family: meta
  • Parameters: 29.8B multimodal
  • Recommended quantization: K-Quant 17GB Q4_K_M
  • Catalogue minimum RAM: 24 GB
  • Catalogue model size: 17 GB
  • Tags: chat, code, reasoning, agentic, vision, long-context, power, quality

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Catalogue tags

  • chat
  • code
  • reasoning
  • agentic
  • vision
  • long-context

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
5
quality
9
coding
9
reasoning
9

Technical notes

Developer
Meta Superintelligence Lab
License
Apache 2.0
Context window
131,072 tokens
Architecture
Dense multimodal causal transformer with a dedicated perception encoder. The release reports about 29.6B total parameters including a roughly 1.8B ViT-G/14 perception encoder, grouped-query attention, local/global attention layers and 131K+ context.

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Comfortable headroomMac mini M4 Pro 48GBMobile workstationMacBook Pro M4 Max 36GBPower-user picks32GB RAM guide

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

Qwen 3.6 35B-A3B 35B (3B active, MoE)Qwen3.8-27B 27BBonsai 27B 27.3B (ternary / 1-bit)Agents-A1 4B 4BNemotron 3.5 Lightning 30B-A3B 30B (3B active, MoE)Ornith-1.5-35B-A3B 35B (3B active, MoE)Agents-A1 35B (3B active, MoE)Gemma 4 12B 12B

Where to go next