unsloth / image-text-to-text updated 1 month ago

Muse-Glimmer-30B-GGUF

Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants. See our Muse Glimmer guide for quantization analysis and instructions. You can now run Muse Glimmer in Unsloth with toggles for thinking. See below for 2-bit Muse Glimmer execute 100+ tool calls inside of Unsloth:

Params
Context
Downloads 30d
1.1 M
Likes
522
Commercial use: allowed apache-2.0 Not gated GGUF View on Hugging Face ↗

Download history

daily snapshots · 33 days
▲ 211 K in the last 30 days (24.4%)
1.1 M819 K
Aug 20Aug 31Sep 11Sep 21

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
Muse-Glimmer-30B-UD-IQ2_XXS.gguf IQ2_XXS 10.7 GB 12.3 GB ✅ Runs comfortably
Muse-Glimmer-30B-UD-IQ2_XS.gguf IQ2_XS 11.5 GB 13.2 GB ✅ Runs comfortably
Muse-Glimmer-30B-UD-IQ2_M.gguf IQ2_M 12.3 GB 14.0 GB ✅ Runs comfortably
Muse-Glimmer-30B-UD-Q2_K_XL.gguf Q2_K_XL 12.4 GB 14.2 GB ✅ Runs comfortably
Muse-Glimmer-30B-UD-IQ3_XXS.gguf IQ3_XXS 13.1 GB 14.9 GB ✅ Runs comfortably
Muse-Glimmer-30B-UD-IQ3_M.gguf IQ3_M 14.1 GB 16.0 GB ✅ Runs comfortably
Muse-Glimmer-30B-Q8_0.gguf Q8_0 29.6 GB 33.1 GB ❌ Won’t fit
Muse-Glimmer-30B-BF16-00001-of-00002.gguf GGUF 29.8 GB 33.3 GB ❌ Won’t fit
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Licence
apache-2.0
First seen on the Hub
2026-08-10
Training datasets
undisclosed
Added to our catalog
2026-08-20
Compare with any image-text-to-text model