Meta

Muse Glimmer 30B

Generally availableOpen weights131K contextReasoning

Summary

Muse Glimmer 30B is an open-weight language model from Meta, released on 10 Aug 2026. It accepts text and images and generates text, with a 131K-token context window and up to 131K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.35 per million input tokens and $1.50 per million output tokens (OpenRouter), across 3 providers we track.

Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperMeta
Release date10 Aug 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licenseapache-2.0 [Hugging Face]
Parameters29.8B [Hugging Face]
Context window131K (131,072 tokens) [models.dev]
Max output131K tokens [models.dev]
Knowledge cutoff4 Jan 2026 [models.dev]
InputText and images [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]
Hugging Facemeta-models/Muse-Glimmer-30B [Hugging Face]

Muse Glimmer 30B API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
NVIDIA NIM
meta/muse-glimmer-30b
FreeFree–131Kmodels.dev, 18 Nov 2026
OpenRouter
meta/muse-glimmer-30b
$0.35$1.50$0.04131KOpenRouter, 18 Nov 2026
Vercel AI Gateway
meta/muse-glimmer-30b
$0.35$1.50$0.04131Kmodels.dev, 18 Nov 2026

Running Muse Glimmer 30B locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)18 GB19 GB19 GB
Q8_0 (8-bit)32 GB33 GB33 GB
FP16 / BF16 (16-bit)60 GB61 GB61 GB

At 4-bit with an 8K conversation, Muse Glimmer 30B needs about 19 GB, so it fits on a graphics card with 24 GB or more, such as the NVIDIA GeForce RTX 3090 24 GB. Check your own hardware, or see Best GPU for local LLMs on our sister site AIPCs.

Frequently asked questions

What is the context window of Muse Glimmer 30B?

Muse Glimmer 30B has a context window of 131,072 tokens (131K) and can generate up to 131,072 tokens in a single response, according to models.dev.

How much does the Muse Glimmer 30B API cost?

Muse Glimmer 30B is listed from $0.35 per million input tokens and $1.50 per million output tokens (OpenRouter). Prices last verified 18 Nov 2026.

Is Muse Glimmer 30B open source?

Muse Glimmer 30B is an open-weight model: its weights are published on Hugging Face as meta-models/Muse-Glimmer-30B under the apache-2.0 license. Check the license terms before commercial use.

When was Muse Glimmer 30B released?

Meta released Muse Glimmer 30B on 10 Aug 2026, according to models.dev.

Which providers offer Muse Glimmer 30B?

We track Muse Glimmer 30B on 3 providers: NVIDIA NIM, OpenRouter, Vercel AI Gateway.

How much VRAM does Muse Glimmer 30B need?

About 19 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 33 GB at 8-bit. The 4-bit model fits on a graphics card with 24 GB or more, such as the NVIDIA GeForce RTX 3090 24 GB. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Command A PlusCohere20 May 2026128K$0.30$1.50Open
Qwen3.8 27BAlibaba (Qwen)14 Aug 2026262K$0.06$1.49Open
Macaron V1 TallMindlab21 Jul 2026262K$0.25$1.43Open
Aion 3.5 MiniAion Labs23 Sept 2026262K$0.70$1.40–
LFM2.5-24B-A2BLiquid13 Oct 2026128K$0.05$0.70Open
Motif 3Motif Technologies2 Nov 2026262K$0.30$1.20Open

Change history

  • OpenRouter price changed: input $0.30 → $0.35, output $1.20 → $1.50 per 1M tokens
  • Max output changed from 16K to 131K
  • Max output changed from 131K to 16K
  • Max output changed from 16K to 131K
  • Max output changed from 131K to 16K
  • Max output changed from 16K to 131K
  • Max output changed from 131K to 16K
  • Max output changed from 16K to 131K
  • Max output changed from 131K to 16K
  • Max output changed from 16K to 131K
  • Max output changed from 131K to 16K
  • Max output changed from 16K to 131K
  • OpenRouter price changed: input $0.35 → $0.30, output $1.50 → $1.20 per 1M tokens
  • Max output changed from 118K to 16K

Sources