AI Desk · AI FingerprintingWithdrawn *

Meta: Muse Glimmer 30B (batch)

meta/muse-glimmer-30b:batch · MetaTokenizer lineage measured

Tokenizer lineage (measured): Llama4
Entered catalogue: 9 August 2026
Measurement: Variant: inherits its base model’s measurement
Evidence confidence: High

Why high: inherited from meta/muse-glimmer-30b: a serving variant shares its base model's tokenizer.

Evidence

✓ inherited from meta/muse-glimmer-30b: a serving variant shares its base model's tokenizer

Compare with Meta: Muse Glimmer 30B

Report a correction

This entry is a serving variant of Meta: Muse Glimmer 30B. A variant shares its base model's tokenizer by construction, so the measurement lives on the base record and this page inherits it.

Identity statement

Meta: Muse Glimmer 30B (batch) is Meta's model. Its measured tokenizer sits with the Llama4 group, which is evidence that it builds on the Llama4 tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against Meta's authorship of the model itself.

What we checked

Four different kinds of evidence, and what each one showed

We checked	What we found	Where it came from
How it counts tokens	Not measured yet	we measured it
How its API is set up	A combination of settings no other listing in the catalogue uses	api_82d00388
How much it can read and write	Reads up to 131,072 tokens at onceOpenRouter's listing shows 117,964 output tokens, which is 90% of the context window, the figure it carries where the provider declares no maximum.	its own listing
Whether it thinks before answering	Always reasons, and cannot be turned off, at xhigh, high, medium, low, medium by default	its own listing

Declared record

What the catalogue claims about this model

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...

Modalities: text+image->text
Declared tokenizer: Other
Prompt price: $0.17 / M tokens
Completion price: $0.75 / M tokens

Supported parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

defaults: {"temperature":1,"top_p":0.95,"top_k":64}

Catalogue entry Weights on Hugging Face

History

Every observation, kept as taken

9 August 2026Enters the OpenRouter catalogue with no declared family.

* Meta: Muse Glimmer 30B (batch) no longer appears in the OpenRouter catalogue, first absent from the snapshot of 5 October 2026. The record stays because the measurements above were real when they were taken and this address has been published.