Back to search results
Qwen3-8B · Q3_K_S
NVIDIA RTX 4080 Super16GBllama.cpp v0.30L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q3_K_S) on NVIDIA RTX 4080 Super with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
168.36 tok/s
Decode
Decode speed
655.5 tok/s
Prefill
Prefill speed
1.91 s
TTFT
Time to first token
13.02 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
17 days ago
Last verified
Performance
- llama.cpp · Q3_K_S (current)Decode 168.36 · Prefill 655.5 ·
- vLLM · IQ2_M Decode 214.44 · Prefill 870.17 ·
- llama.cpp · IQ2_XS Decode 195.22 · Prefill 907.33 ·
Core figures
- Decode (avg)
- 168.36 tok/s
- Prefill (avg)
- 655.5 tok/s
- TTFT (avg)
- 1.91 s
- VRAM (avg)
- 13.02 GB
- MTP acceptance rate
- —
- TTFB
- 1.35 GB
- Power draw
- 248.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q3_K_S
- Framework
- llama.cpp
- Version
- v0.30
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 33
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 4080 Super
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 13.02 GB
- OS
- Ubuntu 22.04
- Driver
- 565.57
- CUDA
- 12.8
- Power draw
- 248.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.30 · Ubuntu 22.04 · CUDA 12.8 · 2048 ctx
168.36 tok/s
Decode
655.5 tok/s
Prefill
1.91 s
TTFT
13.02 GB
VRAM
—
MTP
248.4 W
Power draw
L2 batch seed 2026-10-19: llama.cpp on hw_id=20 running model_id=53 at Q3_K_S