Back to search results
Muse-Glimmer-30B · Q4_K_M
NVIDIA RTX 5080 SUPER24GBvLLM 0.7.3L0 Self-reported
This page aggregates 1 real-world runs of Muse-Glimmer-30B (Q4_K_M) on NVIDIA RTX 5080 SUPER with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
52.3 tok/s
Decode
Decode speed
392.3 tok/s
Prefill
Prefill speed
0.25 s
TTFT
Time to first token
18.7 GB
VRAM
VRAM usage
L0 Self-reported
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · IQ2_XS Decode 94.3 · Prefill 707.3 ·
- vLLM · Q4_K_M (current)Decode 52.3 · Prefill 392.3 ·
- llama.cpp · IQ2_XS Decode 86.5 · Prefill 648.8 ·
- llama.cpp · Q4_K_M Decode 48 · Prefill 360 ·
Core figures
- Decode (avg)
- 52.3 tok/s
- Prefill (avg)
- 392.3 tok/s
- TTFT (avg)
- 0.25 s
- VRAM (avg)
- 18.7 GB
- MTP acceptance rate
- —
- TTFB
- — GB
- Power draw
- — W
Configuration
Member-level fields are taken from the most recent run
- Model
- Muse-Glimmer-30B
- Quantization
- Q4_K_M
- Framework
- vLLM
- Version
- 0.7.3
- Context length
- 4096 tokens
- Batch size
- 512
- GPU layers
- 99
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 5080 SUPER
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 18.7 GB
- OS
- Linux
- Driver
- 570.65
- CUDA
- 12.6
Sources & evidence
1 measured records in total, each traceable to its original source
0.7.3 · Linux · CUDA 12.6 · 4096 ctx
52.3 tok/s
Decode
392.3 tok/s
Prefill
0.25 s
TTFT
18.7 GB
VRAM
—
MTP
— W
Power draw
L0 理论估算（add-1000-records-batch3）