Skip to content

Muse Glimmer 30B on 2× RTX 3090: VRAM, speed and fit

Muse Glimmer 30B at 8-bit runs on the 2× RTX 3090 with 128K of context at about 21 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on 2× RTX 3090 · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
33.0 GB
of 48.0 GB
Context
128K
auto
Speed
21 tok/s
Fast
First reply
1.0 s
2K prompt

Where the memory goes

Model
29.5 GB
Context
1.7 GB
Overhead
1.8 GB
OS
0.0 GB
Free
15.0 GB
Memory
33.0 GB of 48.0 GB
Context
128K tokens · auto
Speed
21 tok/s · fast
First reply
1.0 s for a 2K prompt
Running cost
$11/mo at home · $61/mo on a cloud 2× RTX A4500

Validation: Validated

What Muse Glimmer 30B on 2× RTX 3090 was checked against
CheckTargetResultStatus
Fits in GPU memory48.0 GB usable33.0 GB neededPass
Headroom5% free15.0 GB free (31%)Pass
Context for chat16K or more128KPass
Writing speed15 tok/s or more21 tok/sPass
First replyunder 3 s, 2K prompt1.0 sPass

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
Muse Glimmer 30B
Parameters
29.8B
Precision
8-bit (Q8_0)
Context
128K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
2× RTX 3090
GPU can use
48.0 GB of 48.0 GB

Running cost

At home
$11/mo
500 W at the wall
Renting instead
$61/mo
2× RTX A4500 at $0.50/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.

How to run it

Ollama
ollama run muse-glimmer:30b
llama.cpp
llama-server -hf unsloth/Muse-Glimmer-30B-GGUF
vLLM
vllm serve meta-models/Muse-Glimmer-30B
MLX (Mac)
mlx_lm.chat --model mlx-community/Muse-Glimmer-30B-4bit

Muse Glimmer 30B on similar machines

All machines: Muse Glimmer 30B VRAM requirements. Everything that runs here: what can the 2× RTX 3090 run?

Other models that run on 2× RTX 3090

Questions

Can Muse Glimmer 30B run on 2× RTX 3090?

Muse Glimmer 30B at 8-bit runs on the 2× RTX 3090 with 128K of context at about 21 tokens a second.

Report VR-1DNW9TM, calculated Nov 22, 2026 from published specs, not benchmarked.