What are the hardware requirements for Muse Glimmer 30B FP8 Block?

Muse Glimmer 30B FP8 Block requires approximately 34.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Muse Glimmer 30B FP8 Block and how large is it?

Muse Glimmer 30B FP8 Block is developed by RedHatAI, a model with 30b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Muse Glimmer 30B FP8 Block?

Muse Glimmer 30B FP8 Block is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Muse Glimmer 30B FP8 Block by RedHatAI — VRAM 34.4GB

Name: Muse Glimmer 30B FP8 Block
Author: RedHatAI

Muse Glimmer 30B FP8 Block is an open-source language model by RedHatAI. Features: 30b LLM, VRAM: 34.4GB, License: apache-2.0, LLM Explorer Score: 0.41.

Base model:meta-models/muse-gl... Base model:quantized:meta-mode... Compressed-tensors Conversational Endpoints compatible Fp8 Image-text-to-text Llm-compressor Muse glimmer Region:us Safetensors Sharded Tensorflow Vllm

Model Card on HF 🤗: https://huggingface.co/RedHatAI/Muse-Glimmer-30B-FP8-block

Muse Glimmer 30B FP8 Block Parameters and Internals

LLM Name	Muse Glimmer 30B FP8 Block
Repository 🤗	https://huggingface.co/RedHatAI/Muse-Glimmer-30B-FP8-block
Base Model(s)	Muse Glimmer 30B meta-models/Muse-Glimmer-30B
Model Size	30b
Required VRAM	34.4 GB
Updated	2026-08-13
Maintainer	RedHatAI
Model Type	muse_glimmer
Model Files	28.2 GB: 1-of-2 6.2 GB: 2-of-2
Model Architecture	MuseGlimmerForConditionalGeneration
License	apache-2.0
Model Max Length	131072
Transformers Version	5.15.0.dev0
Tokenizer Class	TokenizersBackend
Padding Token	<\|finetune_right_pad\|>

Rank the Muse Glimmer 30B FP8 Block capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Muse Glimmer 30B FP8 Block

Best Alternatives	Context / RAM	Downloads	Likes
Muse Glimmer 30B	0K / 59.6 GB	0	1052
Muse Glimmer 30B	0K / 59.6 GB	25869	12
Muse Glimmer 30B NVFP4 W4A4	0K / 12.1 GB	10907	3
Muse Glimmer 30B NVFP4	0K / 23.3 GB	1196	6
Muse Glimmer 30B JANG 6M	0K / 27.1 GB	915	2
Muse Glimmer 30B NVFP4	0K / 23.4 GB	566	2
...e Glimmer 30B MXFP8 Vision MLX	0K / 35.2 GB	912	1
... Glimmer 30B Abliterated NVFP4	0K / 29.7 GB	166	3
Muse Glimmer 30B Tq3 G64	0K / 13.5 GB	739	1
Muse Glimmer 30B JANG 4M	0K / 21 GB	507	1

Note: green Score (e.g. "73.2") means that the model is better than RedHatAI/Muse-Glimmer-30B-FP8-block.