MU

Muse Glimmer 30B Heretic v2

MuseGGUF by mradermacherUpdated 2026-08-21
Download on Hugging Face
Parameters27.9B
Context128K
Layers52
Architecturemuse-glimmer
Smallest quant0.0 GB
Quick answer

Muse Glimmer 30B Heretic v2 needs about 17.9 GB of memory at Q4_K_M (a 16.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 22.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.

Muse Glimmer 30B Heretic v2 – a 27.9B‑parameter local LLM for agentic tasks

Muse Glimmer 30B Heretic v2 is a 27.9‑billion‑parameter causal language model optimized for local deployment. It supports multi‑step reasoning, reliable tool use, and multimodal input through a dedicated perception encoder. The model is released under Apache 2.0 and trained on over 100 languages.

Good at

  • End‑to‑end agentic task completion
  • Reliable tool invocation
  • Multimodal reasoning with text and images

Limits

  • Large VRAM requirement for high‑quality quants
  • 131072‑token context length limits long‑form use
  • No external cloud integration required

Best for

  • Building autonomous agents on consumer hardware
  • Debugging and writing code in multi‑turn workflows
  • Interpreting screenshots and documents in chat

Who it’s for. Developers and researchers who need a powerful, locally runnable LLM for agentic applications. The model runs without cloud access and supports a wide range of languages and tools.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.9 GB
Fits Get file →
IQ1_S6.5 GB 7.5 GB
Tight Get file →
IQ1_M7.1 GB 8.0 GB
Tight Get file →
IQ2_XXS8.0 GB 8.9 GB
Too big Get file →
IQ2_XS8.7 GB 9.7 GB
Too big Get file →
IQ2_S9.1 GB 10.1 GB
Too big Get file →
IQ2_M9.8 GB 10.8 GB
Too big Get file →
Q2_K_S10.0 GB 11.0 GB
Too big Get file →
Q2_K10.7 GB 11.6 GB
Too big Get file →
IQ3_XXS11.1 GB 12.1 GB
Too big Get file →
IQ3_XS12.0 GB 12.9 GB
Too big Get file →
Q3_K_S12.5 GB 13.4 GB
Too big Get file →
IQ3_S12.5 GB 13.5 GB
Too big Get file →
IQ3_M12.8 GB 13.8 GB
Too big Get file →
Q3_K_M13.7 GB 14.6 GB
Too big Get file →
Q3_K_L14.7 GB 15.6 GB
Too big Get file →
IQ4_XS15.2 GB 16.2 GB
Too big Get file →
Q4_016.1 GB 17.0 GB
Too big Get file →
Q4_K_S16.1 GB 17.1 GB
Too big Get file →
Q4_K_M16.9 GB 17.9 GB
Too big Get file →
Q4_117.7 GB 18.6 GB
Too big Get file →
Q5_K_S19.3 GB 20.3 GB
Too big Get file →
Q5_K_M19.8 GB 20.7 GB
Too big Get file →
Q6_K22.9 GB 23.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 6.53 GB, memory 7.5 GB at 8k context). For 12 GB VRAM, IQ2_XS (8.71 GB, 9.7 GB). For 16 GB VRAM, Q4_K_M (16.94 GB, 17.9 GB). Larger budgets can use higher‑quality quants such as Q5_K_M or Q6_K.

What GPU do you need for Muse Glimmer 30B Heretic v2?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ1_M (7.1 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q2_K (10.7 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_L (14.7 GB file, about 15.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (22.9 GB file, about 23.8 GB in use).

Which Muse Glimmer 30B Heretic v2 quant should you choose?

Q4_K_M is the usual starting point for Muse Glimmer 30B Heretic v2: it balances file size and quality well. Here it is a 16.9 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemuse-glimmer
Parameters27.9B
Layers52
Trained context131,072 tokens
KV cache (fp16)52 KB per token

Source

Quantized bymradermacher
FamilyMuse
Licenseapache-2.0
Downloads (HF)856
Last updated2026-08-21

Frequently asked questions about Muse Glimmer 30B Heretic v2

How much VRAM does Muse Glimmer 30B Heretic v2 need?

About 17.9 GB at Q4_K_M with an 8K context window. That is the 16.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Muse Glimmer 30B Heretic v2 on an 8 GB GPU?

Yes, with IQ1_M: the 7.1 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Muse Glimmer 30B Heretic v2 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 6.5 GB, IQ1_M is 7.1 GB, IQ2_XXS is 8.0 GB, IQ2_XS is 8.7 GB, IQ2_S is 9.1 GB and 18 more.

What context length does Muse Glimmer 30B Heretic v2 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.7 GB at 32K.

Where can I download Muse Glimmer 30B Heretic v2 GGUF?

The files are on Hugging Face in the mradermacher/Muse-Glimmer-30B-heretic-v2-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Muse Glimmer 30B Heretic v2 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Muse Glimmer 30B Heretic v2 on 8 GB VRAM?

Use the IQ1_S quant; it requires about 7.5 GB of VRAM at 8k context.

Does the model support image input?

Yes, it includes a dedicated perception encoder for interleaved text and images.

What license applies to this model?

The model is released under the Apache 2.0 license.

Other GGUFs of Muse-Glimmer-30B-heretic-v2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Muse models

All Muse →

Other medium models

All medium models →