RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can Muse Glimmer 30B run on the RTX 3080 12GB?

Yes. At 8K context the best fit is Q2_K, using about 11.4 GB of the 11.4 GB usable on the RTX 3080 12GB. Estimated speed ceiling: ~82 tokens/sec.

Better quality with offload: 4-bit (Q4_K_M)

Runs with offload 4-bit (Q4_K_M) at 8K context: 30 of 52 layers on the RTX 3080 12GB (about 10.7 GB) and the other 22 in system RAM (about 7.2 GB). Needs a PC with at least 32 GB of system RAM. Estimated speed: 2.9–5.7 tokens/sec (slow but usable), versus a bandwidth ceiling of ~50 tok/s if it fit fully in VRAM.

llama-server -hf bartowski/Muse-Glimmer-30B-GGUF:Q4_K_M -c 8192 -ngl 30 --no-mmproj

Estimate, not a benchmark. The command downloads the GGUF from Hugging Face. The speed range spans dual-channel DDR4-3200 to DDR5-6000 system RAM; your CPU, RAM speed and llama.cpp version move it. If llama.cpp runs out of GPU memory, lower -ngl by 2-3; if VRAM is left over, raise it for more speed. Recent llama.cpp builds can also pick the split automatically. How we estimate offload.

+ 3.6 GB with image input. The figures on this page are for text only. With image input enabled, the vision projector (mmproj) file loads alongside the model: Q2_K at 8K context then needs about 14.9 GB (no longer fits, so drop one quant or shorten the context). llama.cpp's -hf downloads and loads it automatically unless you add --no-mmproj. Calculator with image input on.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)11.3 GB Tight11.4 GB Tight11.7 GB No12.9 GB No82
3-bit (Q3_K_M)14.5 GB No14.5 GB No14.8 GB No16.0 GB No—
4-bit (Q4_K_M)17.9 GB No17.9 GB No18.2 GB No19.4 GB No—
5-bit (Q5_K_M)20.7 GB No20.7 GB No21.0 GB No22.2 GB No—
6-bit (Q6_K)23.7 GB No23.7 GB No24.0 GB No25.2 GB No—
8-bit (Q8_0)30.4 GB No30.4 GB No30.7 GB No32.0 GB No—
16-bit (F16/BF16)56.4 GB No56.4 GB No56.7 GB No57.9 GB No—

• real GGUF file size. Speed is a bandwidth ceiling (912 GB/s), not a benchmark. Methodology.

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

Muse Glimmer 30B on every GPU and Mac · Every model that runs on the RTX 3080 12GB · Other models that fit 12 GB VRAM · Try other settings in the calculator

Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs

Data: Hugging Face Hub (meta-models/Muse-Glimmer-30B), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.