Back to search results
Qwen3-1.7B · Q3_K_L
NVIDIA RTX 3060 12GB12GBvLLM v0.50L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (Q3_K_L) on NVIDIA RTX 3060 12GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
134.55 tok/s
Decode
Decode speed
711.57 tok/s
Prefill
Prefill speed
1.69 s
TTFT
Time to first token
4.67 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · Q2_K Decode 169.7 · Prefill 583.54 ·
- vLLM · Q3_K_L (current)Decode 134.55 · Prefill 711.57 ·
- vLLM · Q8_0 Decode 84.49 · Prefill 329.46 ·
Core figures
- Decode (avg)
- 134.55 tok/s
- Prefill (avg)
- 711.57 tok/s
- TTFT (avg)
- 1.69 s
- VRAM (avg)
- 4.67 GB
- MTP acceptance rate
- —
- TTFB
- 1.08 GB
- Power draw
- 170.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q3_K_L
- Framework
- vLLM
- Version
- v0.50
- 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)
- 4.67 GB
- OS
- Windows 11 23H2
- Driver
- 555.85
- CUDA
- 12.8
- Power draw
- 170.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.50 · Windows 11 23H2 · CUDA 12.8 · 4096 ctx
134.55 tok/s
Decode
711.57 tok/s
Prefill
1.69 s
TTFT
4.67 GB
VRAM
—
MTP
170.5 W
Power draw
L2 batch seed 2026-10-10: vLLM on hw_id=15 running model_id=55 at Q3_K_L