back to local model checker

Muse Glimmer 30B

ToolsThinkingVisionPopular

Meta · 30B · Dense

Open agentic 30B distilled from Muse Spark — tool use, vision and local recovery on a single GPU

Apache 2.0
Downloads

0

Likes

0

Released

2026-08

Context

128K tokens

Use cases

chatvisionreasoningcode

Your hardware

16 GB Reference Desktop

Quant
Q4_K_M
Memory
15.9 GB
Speed
~13 tok/s
Fit
Barely runs

Quantization options

What is quantization?
QuantBitsVRAMDiskQualityStatus
Q2_K210.1 GB9.2 GBlowDecent · ~20 t/s
Q3_K_M313.9 GB12.8 GBmoderateBarely runs · ~15 t/s
Q4_K_M415.9 GB14.7 GBgoodBarely runs · ~13 t/s
Q5_K_M519.7 GB18.3 GBgoodBarely runs · ~5 t/s
Q6_K623.6 GB22 GBexcellentBarely runs · ~3 t/s
Q8_0831.2 GB29.3 GBexcellentBarely runs · ~2 t/s
F161662 GB58.7 GBlosslessToo heavy · ~1 t/s

About this model

Muse Glimmer 30B (muse glimmer 30b) is a 30B dense transformer from Meta in the Muse family, designed primarily for chat, vision, reasoning, code workflows. Native reasoning/thinking tokens expand output length per query, so reserve extra KV cache headroom. Supports structured tool calling; use Q4_K_M or higher when strict JSON schema adherence matters. Supports up to 128K context tokens; start at 4K–8K with Q8_0 KV cache on tight GPUs.

Hardware planning baselines start at 16.8 GB minimum memory and 27.9 GB recommended memory. At Q4_K_M, weights plus baseline runtime overhead use roughly 15.9 GB of RAM/VRAM and 14.7 GB of disk space. As a 30B dense checkpoint, every parameter participates in each token forward pass, meaning decoding speed scales linearly with GPU memory bandwidth and drops sharply if layers spill over PCIe into host DDR5 RAM.

Deploy Muse Glimmer 30B locally via Ollama (`muse-glimmer`), LM Studio, or Ollama with Flash Attention enabled. Under Apache License 2.0, review official weight cards before commercial redistribution.

Highlights

  • Local Fit Baseline16.8 GB minimum and 27.9 GB recommended RAM/VRAM.
  • Primary QuantQ4_K_M targets 15.9 GB memory and 14.7 GB disk.
  • Context & Capabilities128K max context · Dense · Tool calling · Reasoning.

System requirements by device

Memory planning targets 16.8 GB minimum RAM/VRAM and 27.9 GB recommended memory. The baseline quant is Q4_K_M, estimated at 15.9 GB memory and 14.7 GB disk. Actual runtime usage shifts with context length, KV cache precision, and OS background overhead.

DeviceNotes
Mac (Apple silicon)Use unified memory headroom (~75% physical RAM max) as the primary fit signal. Start with Q4_K_M and close heavy browser tabs first.
Windows / Linux GPUKeep weights plus KV cache inside dedicated VRAM so Windows WDDM does not spill layers over PCIe into Shared GPU Memory.
Phones & Compact Edge BoardsNot practical on phones (16.8 GB min RAM exceeds Android LMK and iOS Jetsam limits). Pick a 2B–4B model on mobile.

Start with a short session and leave memory for the operating system. A file fitting on disk does not guarantee that it will load in memory.

Estimated memory by quantization

These are rough estimates, not tested minimum requirements. Check the actual file and runtime documentation; context, offloading and operating-system overhead can change the memory needed.

Quant TierEstimated memoryDisk SizeQuality
Q2_K10.1 GB9.2 GBlow
Q3_K_M13.9 GB12.8 GBmoderate
Q4_K_M15.9 GB14.7 GBgood
Q5_K_M19.7 GB18.3 GBgood
Q6_K23.6 GB22.0 GBexcellent
Q8_031.2 GB29.3 GBexcellent
F1662.0 GB58.7 GBlossless

How to run Muse Glimmer 30B on your device

Start with a short prompt and the smallest quant that still gives the quality you need. A clean first run is more useful than loading a larger file with no memory headroom.

Mac

Run Muse Glimmer 30B on Mac

  1. Install Ollama or LM Studio on macOS Apple Silicon.
  2. Pull Q4_K_M (15.9 GB) first and confirm it stays below ~75% of your Mac's unified memory.
  3. Enable Flash Attention and cap initial context at 8K until memory pressure stays below 27.9 GB.
  4. Consult the Mac guide for Activity Monitor tuning and Metal offload tips.
Device how-to guide
Windows

Run Muse Glimmer 30B on Windows

  1. Install LM Studio for Windows for visual VRAM inspection, or Ollama when you want a localhost API endpoint.
  2. Load Q4_K_M (~15.9 GB) and verify Dedicated GPU Memory stays within VRAM without spilling into Shared GPU Memory.
  3. Reserve at least 16.8 GB memory minimum and target 27.9 GB for comfortable context growth.
  4. Enable Q8_0 KV cache or drop one quant tier if generation slows down over PCIe.
Device how-to guide

Muse Glimmer 30B vs alternatives

ModelParamsContextMin RAMLicense
Muse Glimmer 30B30B128K16.8 GBApache 2.0
Qwen 3 30B-A3B30B (3.3B active)128K16.8 GBApache 2.0
Nemotron 3 Nano 30B30B (3B active)1M16.8 GBNVIDIA Open
Granite 4.1 30B30B128K16.8 GBApache 2.0
North Mini Code30B (3B active)256K16.8 GBApache 2.0
Qwen 3 Coder 30B-A3B30B (3B active)256K16.8 GBApache 2.0

Use this table to choose the smallest nearby model that still matches the job. A related model with lower RAM can be the better local choice when the current page fits only at the edge of available memory.

Frequently asked questions

What is Muse Glimmer 30B?
Muse Glimmer 30B is a 30B dense transformer from Meta, supporting up to 128K tokens with 16.8 GB minimum RAM and 27.9 GB recommended RAM.
How do I download and install muse glimmer 30b?
Download a GGUF build for Muse Glimmer 30B, start with Q4_K_M, and confirm the model fits locally before increasing context or quant quality.
How much VRAM or RAM does Muse Glimmer 30B require?
At Q4_K_M, Muse Glimmer 30B occupies roughly 15.9 GB of active memory and 14.7 GB on disk. Add 2–6 GB of spare headroom for KV cache buffers, runtime scratch space, and OS apps (27.9 GB recommended).
What is the best way to run Muse Glimmer 30B locally?
Use `ollama run muse-glimmer` for a quick CLI/API setup, or load Q4_K_M in LM Studio or llama.cpp with Flash Attention enabled when you want explicit KV cache and layer control.
Can Muse Glimmer 30B run on Android or iPhone?
Muse Glimmer 30B requires 16.8 GB minimum memory, placing it outside practical 8 GB smartphone limits. Run it on a 16 GB+ Mac or desktop GPU instead, and pick a 2B–4B checkpoint for phones.
How does Muse Glimmer 30B compare to Qwen 3 30B-A3B?
Qwen 3 30B-A3B (30B, 16.8 GB min RAM) sits closest in size. Compare active parameters, context ceiling (128K vs 128K), and license terms (Apache 2.0) before switching.