Muse Glimmer 30B — oQ8

A native Apple-silicon conversion of meta-models/Muse-Glimmer-30B, quantized with oMLX's optimized oQ8 recipe for text-and-image inference with MLX-VLM.

Original model · MLX-VLM · MLX · More TensorFold conversions

About this conversion

This repository contains an oMLX-optimized oQ8 conversion of Muse Glimmer 30B, a dense agentic language model with a dedicated perception encoder. It preserves the upstream tokenizer, ATEM chat template, image processor configuration, generation configuration, licence, and usage policy.

At an 8-bit base there are no higher-bit per-module overrides. Both quantization and quantization_config record the oQ8 recipe.

[!IMPORTANT] Muse Glimmer support was validated against the official MLX-VLM source at commit 5262cb6, reporting package version 0.6.12. An older MLX-VLM or oMLX bundle may report Model type muse_glimmer not supported; update to a build containing the upstream Muse implementation before loading this checkpoint.

Apple-silicon performance

This checkpoint was load-tested, text-generation tested, and benchmarked on:

A warmed local text-only test produced:

The decode figure is the median of three greedy 256-token runs after a full 256-token Metal-kernel warm-up. It is a practical local reference, not a controlled cross-platform benchmark. Prompt length, images, context growth, sampler settings, memory pressure, thermal state, and runtime versions can materially change performance. Image prefill is not included in this decode benchmark.

Runtime setup

Until Muse Glimmer support reaches the MLX-VLM build supplied by your application, install the exact official source revision used for validation:

python -m pip install \
  "mlx-vlm @ git+https://github.com/Blaizzy/mlx-vlm.git@5262cb6a27c797c5c3daf64b17d757924c5c474f"

Download the checkpoint if a local copy is preferred:

hf download TensorFold/Muse-Glimmer-30B-oQ8 \
  --local-dir ~/.omlx/models/TensorFold/Muse-Glimmer-30B-oQ8

Text generation

from mlx_vlm import generate, load


model, processor = load("TensorFold/Muse-Glimmer-30B-oQ8")
tokenizer = processor.tokenizer if hasattr(processor, "tokenizer") else processor
messages = [
    {"role": "user", "content": "Explain unified memory on Apple silicon."}
]
prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    reasoning_strength="medium",
)
result = generate(
    model,
    processor,
    prompt,
    max_tokens=512,
    temperature=0.0,
)
print(result.text)

Muse Glimmer supports low, medium, high, and xhigh reasoning strengths. Higher settings can spend more tokens reasoning before returning the final answer.

Image and text generation

The multimodal path was smoke-tested locally with a real image. Include an image content item so the ATEM template emits the required patch token:

from mlx_vlm import generate, load


model, processor = load("TensorFold/Muse-Glimmer-30B-oQ8")
tokenizer = processor.tokenizer if hasattr(processor, "tokenizer") else processor
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "Describe this image in one sentence."},
        ],
    }
]
prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)
result = generate(
    model,
    processor,
    prompt,
    image=["image.jpg"],
    max_tokens=256,
    temperature=0.0,
)
print(result.text)

Architecture

Muse Glimmer combines a dense causal transformer with a dedicated perception encoder for interleaved text and image input.

The model supports agentic task completion, tool use through the upstream ATEM protocol, controllable reasoning effort, multilingual input, failure recovery, and multimodal understanding. See the original model card for upstream benchmarks, training details, intended uses, limitations, and safety guidance.

Conversion and validation notes

• Source weights: upstream BF16 checkpoint at revision a4e59da52a7bc87ae7251dd5545c0dd437c44b68.
• Quantization mode: oQ8 affine, group size 64, without higher-bit overrides.
• The upstream tokenizer, ATEM chat template, processor configuration, generation configuration, licence, and usage policy are included.
• All 2,272 converted tensors and all 7 indexed shards were checked locally.
• The checkpoint was exercised through full text generation; the Muse architecture was also smoke-tested with image input.
• Quantization can reduce output quality relative to BF16. Use a higher-precision variant when quality matters more than memory use.
• This release does not include or claim support for the upstream speculative drafter.

This is a community conversion, not an official Meta release. Validate quality, safety, and numerical behaviour on representative workloads before production use.

Licence, usage policy, and attribution

The upstream model is released under the Apache License 2.0. The upstream LICENSE and USAGE_POLICY.md files are included in this repository; use is subject to both the licence and the upstream usage policy.

All model design, training, benchmark, and upstream documentation credit belongs to Meta and the original contributors. The MLX conversion, Apple-silicon validation, compatibility work, and model card are provided by TensorFold.

Choose for your Mac

64GB Macs · 128GB Macs · 256GB Macs

Published peak memory: 35.35 GB; estimated starting tier: 64GB, leaving about 28 GB nominal headroom. The collections use published M3 Studio peaks with at least 25% nominal headroom; fit on other Macs is an estimate, and full context is not guaranteed. Start with short context and one request.

Runtime and evidence

The exact tested oMLX application version is not recorded here; a library version is not an app version. The original performance tables retain their benchmark conditions and speed figures; this documentation update adds no new test results.

Quick start and demo prompt

hf download TensorFold/Muse-Glimmer-30B-oQ8 --local-dir ./models/Muse-Glimmer-30B-oQ8

Add the downloaded folder to oMLX model directories, refresh the list, and follow this card's architecture and MTP compatibility requirements before loading.

Try this in a new chat with a 128-token output limit:

Explain why the sky looks blue in three short sentences.

This is a demo prompt to try, not a recorded successful run; a captured demonstration for this documentation update is not yet available.

Follow TensorFold for new Apple Silicon releases and fixes.