GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

bluevoid-pl/Muse-Glimmer-30B-GGUF overview

WARNING Muse Glimmer 30B is currently partially supported by llama.cpp and ollama. It might not output to cli at all, use webinterface instead. Make sure to us…

ggufMetaGGUFbase_model:meta-models/Muse-Glimmer-30Bbase_model:quantized:meta-models/Muse-Glimmer-30Blicense:apache-2.0endpoints_compatibleregion:usimatrixconversational

Runs locally from ~7.41 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
47
Likes
0
Pipeline

Repository Files & Downloads

3 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
Muse-Glimmer-30B-IQ2_XXS.ggufGGUFIQ2_XXS7.41 GBDownload
Muse-Glimmer-30B-Q4_K_M.ggufGGUFQ4_K_M15.77 GBDownload
Muse-Glimmer-30B-Q8_0.ggufGGUFQ8_027.58 GBDownload

Model Details

Model IDbluevoid-pl/Muse-Glimmer-30B-GGUF
Authorbluevoid-pl
Pipeline
Licenseapache-2.0
Base modelmeta-models/Muse-Glimmer-30B
Last modified2026-08-15T17:38:00.000Z

Model README

---

license: apache-2.0

base_model:

  • meta-models/Muse-Glimmer-30B

tags:

  • Meta
  • GGUF

---

> [!WARNING]

> Muse-Glimmer-30B is currently partially supported by llama.cpp and ollama. It might not output to cli at all, use webinterface instead.

> Make sure to use llama.cpp version greater than b10430, model will fail to load on older version.

This is gguf of meta-models/Muse-Glimmer-30B provided by bluevoid-pl

Run bluevoid-pl/Muse-Glimmer-30B-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models