Muse-Glimmer-30B-Abliterated-MLX-3bit

Ishowbackup/Muse-Glimmer-30B-Abliterated-MLX-3bit

Muse-Glimmer-30B-Abliterated-MLX-3bit is a image-text-to-text model from Ishowbackup. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.

Downloads · 30 days

21% of all-time downloads

All-time downloads

234

Public

Parameters

29.8B

16 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors15.9 GB · 100%

Parameter types

How the weights are stored.

U3227.9B · 94%

Try a prompt

Base models

Blackfrost-Research/Muse-Glimmer-30B-Abliterated-BF16

Model card

From the Hugging Face model README

<div align="center"> <h1>MUSE-GLIMMER-30B-ABLITERATED-MLX-3bit</h1> <h3>3-bit MLX for Apple Silicon — smallest footprint</h3> <p><strong>Built by <a href="https://x.com/Blackfrost_AI">Blackfrost</a> · Las Vegas, NV</strong></p> <p> <img src="https://img.shields.io/badge/MLX_3bit-1f2937?style=for-the-badge" /> <img src="https://img.shields.io/badge/0%2F450_refusals-047857?style=for-the-badge" /> <img src="https://img.shields.io/badge/Abliterated-1f2937?style=for-the-badge" /> <img src="https://img.shields.io/badge/Apple_MLX-047857?style=for-the-badge" /> </p> </div>

Refusal benchmark — R1-HARMFUL-BENCH-450

Measured on the abliterated model — quantization holds it, no refusal snapback:

Metric	Result
True refusal (harmful, n=300)	0 / 300 = 0.0%
True refusal (full 450)	0 / 450 = 0.0%
Substring-harmful	0 / 300
Substring-all	2 / 450 (XSTest false positives)
Errors	0

Why this model exists

Muse Glimmer is Meta Superintelligence Labs' 30B agentic, on-device model. This is the abliterated build — refusal behavior removed via a Blackfrost weight-change process — packaged as MLX 3-bit — ~15 GB for Apple-silicon Macs. The local footprint is the product.

Specifications


Architecture	`muse_glimmer` — dense, 52 layers, hidden 6656, GQA (32 q / 2 kv), sliding-window attention, + vision tower
Base	`meta-models/Muse-Glimmer-30B` — Meta, Apache-2.0
Transform	Abliterated — refusal behavior removed via a Blackfrost weight-change process; multimodal capability intact
Format	MLX 3-bit — ~15 GB
Context	131,072

Serving (Apple Silicon / MLX)

pip install mlx-lm
# one-off generate:
mlx_lm.generate --model Blackfrost-Research/Muse-Glimmer-30B-Abliterated-MLX-3bit --prompt "Write a binary search in Python." --max-tokens 1024
# OpenAI-compatible server:
mlx_lm.server --model Blackfrost-Research/Muse-Glimmer-30B-Abliterated-MLX-3bit --port 8080

Or open it directly in LM Studio (MLX runtime) on an Apple-silicon Mac.

Sampling (Meta): temperature 1.0, top_p 0.95, top_k 64. It's a heavy thinker — use a generous max_tokens (≥ 1024) and steer depth with a Reasoning strength: low/medium/high/xhigh system line. Reasoning is returned separately from the final answer.

<div align="center"> <p>Built by <a href="https://x.com/Blackfrost_AI">Blackfrost</a> · Las Vegas, NV. Not affiliated with Meta.</p> </div>

Task: Image-Text-to-Text
Library: mlx
Type: muse_glimmer
License: apache-2.0
Created: Aug 15, 2026
Updated: Aug 15, 2026