Back to search results
Qwen3.8-9B · Q3_K_S
NVIDIA RTX 409024GBvLLM v0.22L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (Q3_K_S) on NVIDIA RTX 4090 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
144.28 tok/s
Decode
Decode speed
508.23 tok/s
Prefill
Prefill speed
1.4 s
TTFT
Time to first token
14.38 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 144.28 · Prefill 508.23 ·
- Strata · Q4_K_M Decode 168.91 · Prefill 879.31 ·
- vLLM · IQ4_XS Decode 131.27 · Prefill 643.79 ·
- vLLM · Q2_K Decode 152.53 · Prefill 504.65 ·
- Ollama · IQ3_XS Decode 121.23 · Prefill 396.17 ·
Core figures
- Decode (avg)
- 144.28 tok/s
- Prefill (avg)
- 508.23 tok/s
- TTFT (avg)
- 1.4 s
- VRAM (avg)
- 14.38 GB
- MTP acceptance rate
- —
- TTFB
- 1.15 GB
- Power draw
- 303.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- Q3_K_S
- Framework
- vLLM
- Version
- v0.22
- Context length
- 2048 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 4090
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 14.38 GB
- OS
- Windows 11 23H2
- Driver
- 570.86
- CUDA
- 12.8
- Power draw
- 303.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.22 · Windows 11 23H2 · CUDA 12.8 · 2048 ctx
144.28 tok/s
Decode
508.23 tok/s
Prefill
1.4 s
TTFT
14.38 GB
VRAM
—
MTP
303.1 W
Power draw
L2 batch seed 2026-10-19: vLLM on hw_id=1 running model_id=52 at Q3_K_S