Models › Muse-Glimmer-30B

Muse-Glimmer-30B: VRAM needs and speed by GPU

At UD-Q4_K_XL, Muse-Glimmer-30B needs about 17.4 GB of VRAM. No measured runs yet. Speeds below are estimates. Submit a run.

27.85B parameters · license: apache-2.0 · 131,072-token context · GGUF published Aug 10, 2026 · GGUF files on Hugging Face

Memory needed per quantization

QuantFile sizeNeeds (estimate)Smallest card it fits
UD-IQ2_XXS10.7 GB12.2 GB16 GB cards
UD-IQ2_XS11.5 GB13.0 GB16 GB cards
UD-IQ2_M12.3 GB13.8 GB16 GB cards
UD-Q2_K_XL12.4 GB13.9 GB16 GB cards
UD-IQ3_XXS13.1 GB14.6 GB16 GB cards
UD-Q3_K_XL13.4 GB14.9 GB16 GB cards
UD-IQ3_M14.1 GB15.6 GB24 GB cards
UD-Q4_K_XL15.9 GB17.4 GB24 GB cards
UD-Q5_K_M19.2 GB20.7 GB24 GB cards
UD-Q5_K_L19.8 GB21.3 GB24 GB cards
UD-Q5_K_XL21.8 GB23.3 GB24 GB cards
UD-Q6_K_XL26.3 GB27.8 GB32 GB cards
Q8_029.6 GB31.1 GB32 GB cards
UD-Q8_K_XL32.3 GB33.8 GB48 GB cards
BF1655.7 GB57.2 GB96 GB cards

Expected speed on popular hardware

HardwareBest quant that fitsExpected tok/s
NVIDIA RTX 3060Does not fit
NVIDIA RTX 4060 TiDoes not fit
NVIDIA RTX 3090UD-Q5_K_M34.2 estimate
NVIDIA RTX 4090UD-Q5_K_M37.9 estimate
NVIDIA RTX 5090Q8_038.8 estimate
AMD Radeon RX 7900 XTXUD-Q5_K_M38.0 estimate
Apple M4 Pro (20-core GPU) (64 GB)Q8_07.8 estimate
Apple M3 Max (40-core GPU) (64 GB)Q8_011.4 estimate
AMD Ryzen AI Max+ 395 (Radeon 8060S)Q8_07.0 estimate

Check your own card

Too big for your card?

Run Muse-Glimmer-30B on a rented 24-80 GB GPU by the hour.

Rent a bigger GPU on RunPod

Affiliate link: if you sign up, RigBench may earn a referral credit. It never affects rankings or numbers.