What are the hardware requirements for Muse Glimmer Q4 MLX?

Muse Glimmer Q4 MLX requires approximately 15.7 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Muse Glimmer Q4 MLX and how large is it?

Muse Glimmer Q4 MLX is developed by RadixArk, a model with 30b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Muse Glimmer Q4 MLX perform on standard benchmarks?

Muse Glimmer Q4 MLX has the following published scores: LMSYS ELO 1426. Compare against reference models on this page or on the LLM Explorer leaderboards.

Muse Glimmer Q4 MLX by RadixArk — VRAM 15.7GB, 128K context

Name: Muse Glimmer Q4 MLX
Author: RadixArk

Muse Glimmer Q4 MLX is an open-source language model by RadixArk. Features: 30b LLM, VRAM: 15.7GB, Context: 128K, Quantized, LLM Explorer Score: 0.45, ELO: 1426.

4-bit Apple-silicon Base model:meta-models/muse-gl... Base model:quantized:meta-mode... Conversational Custom code Mlx Muse-glimmer Muse glimmer Q4 Quantized Region:us Safetensors Sglang Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/RadixArk/Muse-Glimmer-q4-MLX

Muse Glimmer Q4 MLX Benchmarks

LMSys ELO 1426 vs 1272 (so35) 12.1%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Muse Glimmer Q4 MLX Parameters and Internals

LLM Name	Muse Glimmer Q4 MLX
Repository 🤗	https://huggingface.co/RadixArk/Muse-Glimmer-q4-MLX
Base Model(s)	Muse Glimmer 30B meta-models/Muse-Glimmer-30B
Model Size	30b
Required VRAM	15.7 GB
Updated	2026-08-14
Maintainer	RadixArk
Model Type	muse_glimmer
Model Files	5.3 GB: 1-of-3 5.4 GB: 2-of-3 5.0 GB: 3-of-3
Quantization Type	q4
Model Architecture	MuseGlimmerForConditionalGeneration
Context Length	131072
Model Max Length	131072
Tokenizer Class	TokenizersBackend
Padding Token	<\|finetune_right_pad\|>
Vocabulary Size	202048

Rank the Muse Glimmer Q4 MLX 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 Q4 MLX

Best Alternatives	Context / RAM	Downloads	Likes
Muse Glimmer 30B 8bit	0K / 11.6 GB	2935	2
Muse Glimmer 30B OptiQ 4bit	0K / 19.9 GB	360	1
Muse Glimmer 30B MLX 8bit	0K / 33.4 GB	107	1
...use Glimmer 30B Hermes Agentic	0K / 59.6 GB	37	2
Muse Glimmer 30B 4bit	0K / 19.4 GB	0	11
...e Glimmer 30B Unsloth Bnb 4bit	0K / 22.2 GB	0	7
...immer 30B Abliterated MLX 6bit	0K / 26.4 GB	1010	1
Muse Glimmer 30B	0K / 59.6 GB	0	1052
Muse Glimmer 30B	0K / 59.6 GB	25869	12
Muse Glimmer 30B AWQ INT4	0K / 24.1 GB	985	8

Note: green Score (e.g. "73.2") means that the model is better than RadixArk/Muse-Glimmer-q4-MLX.