Back to search results
Qwen3-8B · Q3_K_S
NVIDIA RTX 3060 12GB12GBvLLM v0.34L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q3_K_S) on NVIDIA RTX 3060 12GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
73.32 tok/s
Decode
Decode speed
238.24 tok/s
Prefill
Prefill speed
0.61 s
TTFT
Time to first token
11.4 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
16 days ago
Last verified
Performance
- vLLM · Q3_K_S (current)Decode 73.32 · Prefill 238.24 ·
- Ollama · IQ3_S Decode 58.42 · Prefill 197.59 ·
- llama.cpp · IQ2_M Decode 70.85 · Prefill 298.67 ·
- vLLM · IQ3_S Decode 64 · Prefill 232.21 ·
- llama.cpp · IQ3_S Decode 81.43 · Prefill 366.11 ·
Core figures
- Decode (avg)
- 73.32 tok/s
- Prefill (avg)
- 238.24 tok/s
- TTFT (avg)
- 0.61 s
- VRAM (avg)
- 11.4 GB
- MTP acceptance rate
- —
- TTFB
- 0.59 GB
- Power draw
- 146.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q3_K_S
- Framework
- vLLM
- Version
- v0.34
- Context length
- 4096 tokens
- Batch size
- 8
- GPU layers
- 999
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 3060 12GB
- Nominal VRAM
- 12 GB
- Measured VRAM (avg)
- 11.4 GB
- OS
- Ubuntu 22.04
- Driver
- 565.57
- CUDA
- 12.8
- Power draw
- 146.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.34 · Ubuntu 22.04 · CUDA 12.8 · 4096 ctx
73.32 tok/s
Decode
238.24 tok/s
Prefill
0.61 s
TTFT
11.4 GB
VRAM
—
MTP
146.9 W
Power draw
L2 batch seed 2026-10-19: vLLM on hw_id=15 running model_id=53 at Q3_K_S