Back to search results
Qwen3-4B · Q3_K_S
NVIDIA RTX 407012GBvLLM v0.30L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B (Q3_K_S) on NVIDIA RTX 4070 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
110.14 tok/s
Decode
Decode speed
421.19 tok/s
Prefill
Prefill speed
1.78 s
TTFT
Time to first token
7.56 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- vLLM · Q3_K_S (current)Decode 110.14 · Prefill 421.19 ·
- vLLM · Q4_K_M Decode 88.36 · Prefill 459.98 ·
Core figures
- Decode (avg)
- 110.14 tok/s
- Prefill (avg)
- 421.19 tok/s
- TTFT (avg)
- 1.78 s
- VRAM (avg)
- 7.56 GB
- MTP acceptance rate
- —
- TTFB
- 0.88 GB
- Power draw
- 238 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B
- Quantization
- Q3_K_S
- Framework
- vLLM
- Version
- v0.30
- Context length
- 32768 tokens
- Batch size
- 16
- 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 4070
- Nominal VRAM
- 12 GB
- Measured VRAM (avg)
- 7.56 GB
- OS
- macOS 15.0
- Driver
- 560.94
- CUDA
- 12.6
- Power draw
- 238 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.30 · macOS 15.0 · CUDA 12.6 · 32768 ctx
110.14 tok/s
Decode
421.19 tok/s
Prefill
1.78 s
TTFT
7.56 GB
VRAM
—
MTP
238 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=45 running model_id=54 at Q3_K_S