Back to search results
Qwen3.8-9B · Q2_K
NVIDIA RTX 409024GBvLLM v0.55L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (Q2_K) on NVIDIA RTX 4090 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
152.53 tok/s
Decode
Decode speed
504.65 tok/s
Prefill
Prefill speed
0.29 s
TTFT
Time to first token
12.5 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · Q2_K (current)Decode 152.53 · Prefill 504.65 ·
- Ollama · IQ3_XS Decode 121.23 · Prefill 396.17 ·
Core figures
- Decode (avg)
- 152.53 tok/s
- Prefill (avg)
- 504.65 tok/s
- TTFT (avg)
- 0.29 s
- VRAM (avg)
- 12.5 GB
- MTP acceptance rate
- —
- TTFB
- 1.22 GB
- Power draw
- 286.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- Q2_K
- Framework
- vLLM
- Version
- v0.55
- Context length
- 8192 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 4090
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 12.5 GB
- OS
- Ubuntu 24.04
- Driver
- 570.86
- CUDA
- 12.4
- Power draw
- 286.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.55 · Ubuntu 24.04 · CUDA 12.4 · 8192 ctx
152.53 tok/s
Decode
504.65 tok/s
Prefill
0.29 s
TTFT
12.5 GB
VRAM
—
MTP
286.5 W
Power draw
L2 batch seed 2026-10-10: vLLM on hw_id=1 running model_id=52 at Q2_K