Model Intelligence Sheet
ggml-org/Muse-Glimmer-30B-GGUF overview
Muse Glimmer 30B Run it in the Llama app: https://llama.app Or from the terminal: bash llama serve hf ggml org/Muse Glimmer 30B GGUF Source models https://hugg…
Runs locally from ~1.35 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
8 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Muse-Glimmer-30B-BF16.gguf | GGUF | BF16 | 51.90 GB | Download |
| Muse-Glimmer-30B-Q4_K_M.gguf | GGUF | Q4_K_M | 17.92 GB | Download |
| Muse-Glimmer-30B-Q8_0.gguf | GGUF | Q8_0 | 27.58 GB | Download |
| dflash-Muse-Glimmer-30B-BF16.gguf | GGUF | BF16 | 4.77 GB | Download |
| dflash-Muse-Glimmer-30B-Q4_0.gguf | GGUF | Q4_0 | 1.35 GB | Download |
| dflash-Muse-Glimmer-30B-Q8_0.gguf | GGUF | Q8_0 | 2.54 GB | Download |
| mmproj-Muse-Glimmer-30B-BF16.gguf | GGUF | BF16 | 3.58 GB | Download |
| mmproj-Muse-Glimmer-30B-Q8_0.gguf | GGUF | Q8_0 | 1.91 GB | Download |
Model Details
| Model ID | ggml-org/Muse-Glimmer-30B-GGUF |
|---|---|
| Author | ggml-org |
| Pipeline | image-text-to-text |
| License | apache-2.0 |
| Base model | meta-models/Muse-Glimmer-30B |
| Last modified | 2026-10-19T14:16:18.000Z |
Model README
---
license: apache-2.0
pipeline_tag: image-text-to-text
tags:
- gguf
- quantized
base_model:
- meta-models/Muse-Glimmer-30B
---
Muse-Glimmer-30B
Run it in the Llama app: https://llama.app
Or from the terminal:
llama serve -hf ggml-org/Muse-Glimmer-30B-GGUFSource models
- https://huggingface.co/meta-models/Muse-Glimmer-30B
- https://huggingface.co/meta-models/Muse-Glimmer-30B-assistant
Notes
- Includes a Q8_0 mmproj for the vision encoder.
- Includes a DFlash drafter sidecar (BF16, Q8_0 and Q4_0) for speculative decoding.
TODOs
- add info
> [!IMPORTANT]
> This model is automatically converted using https://github.com/ggml-org/convert
Run ggml-org/Muse-Glimmer-30B-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models