How much VRAM does Muse Glimmer 30B need?

At Q4_K_M with 8K context: 18.1GB weights + 0.4GB KV cache + 1.5GB runtime overhead = 20.1GB total. RX 7900 XTX offers 24.0GB usable VRAM, so the verdict is: Tight fit.

What is the best quantization for Muse Glimmer 30B on RX 7900 XTX?

Q5_K_M — the highest tier that still fits within 24.0GB usable VRAM at 8K context. Lower tiers (Q3/Q2) fit too but cost noticeable quality.

How fast does Muse Glimmer 30B run on RX 7900 XTX?

About 34 tokens/s at Q5_K_M (theoretical estimate, ±30% in real-world use).

Can RX 7900 XTX run Muse Glimmer 30B?

⚠️ Tight

Muse Glimmer 30B @ Q4_K_M · 8K context

Needed

20.1 GB

Usable

24.0 GB

VRAM breakdown

Weights (Q4_K_M)	18.1 GB
KV cache (8K context)	0.4 GB
Runtime overhead	1.5 GB
Total	20.1 GB

Computed at 8K context with fp16 KV cache. Longer contexts need more VRAM — use the VRAM calculator for other settings.

Recommended quantization

Q5_K_M

Estimated generation speed

~34 tok/s @ Q5_K_M

Theoretical estimates based on published architecture data and measured GGUF sizes; real-world speed varies ±30%.

Smaller models this GPU runs well

Other GPUs that run Muse Glimmer 30B

FAQ

How much VRAM does Muse Glimmer 30B need?: At Q4_K_M with 8K context: 18.1GB weights + 0.4GB KV cache + 1.5GB runtime overhead = 20.1GB total. RX 7900 XTX offers 24.0GB usable VRAM, so the verdict is: Tight fit.
What is the best quantization for Muse Glimmer 30B on RX 7900 XTX?: Q5_K_M — the highest tier that still fits within 24.0GB usable VRAM at 8K context. Lower tiers (Q3/Q2) fit too but cost noticeable quality.
How fast does Muse Glimmer 30B run on RX 7900 XTX?: About 34 tokens/s at Q5_K_M (theoretical estimate, ±30% in real-world use).

Check another combination in the GPU Checker →

Data verified 2026-09-01