Q4_K_M
The conversion repository lists Muse-Glimmer-30B-KQuant-17GB-Q4_K_M.gguf at 16.8 GB; its rounded decimal file size is converted to GiB for planning. This does not include context or runtime memory.
- Bits per weight
- 4.5
- Model size
- 15.65 GiB
Model catalog
Muse Glimmer 30B
Meta's 30B multimodal model with a dedicated perception encoder. The listed text-model GGUF does not include its separate projector/encoder file.
Model overview
Available quantizations
Lower-bit quantizations generally use less memory. The compatibility calculator uses these candidates and its transparent approximate memory assumptions; it does not make a performance guarantee.
Compatibility notes
Estimates use the cataloged model-weight size (or a parameter-based estimate), apply weight overhead, and include standard runtime overhead. They do not include context/KV-cache memory. Real requirements vary with runtime, drivers, and other system use. A model page cannot determine compatibility without your hardware profile; use the calculator for that assessment.
Meta Muse Glimmer 30B model card; verified value, last verified 2026-09-29. Meta identifies a 30B model under Apache-2.0. Its official GGUF repository provides a text-model file and separate multimodal projector/encoder files, so the auxiliary file is outside the listed weight estimate. View source
Multimodal memory scope: This estimate excludes the separate vision/projector file and its runtime memory. Meta Muse Glimmer 30B GGUF repository