Back to search results
Qwen3.8-9B · Q8_0
NVIDIA RTX 509032GBvLLM v0.44L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (Q8_0) on NVIDIA RTX 5090 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
152.59 tok/s
Decode
Decode speed
801.24 tok/s
Prefill
Prefill speed
0.81 s
TTFT
Time to first token
23.84 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- Ollama · Q3_K_S Decode 237.4 · Prefill 1150.93 ·
- Strata · Q3_K_L Decode 349.94 · Prefill 1124.59 ·
- vLLM · Q3_K_S Decode 286.31 · Prefill 1535.26 ·
- vLLM · Q8_0 (current)Decode 152.59 · Prefill 801.24 ·
- Strata · IQ1_S Decode 313.75 · Prefill 1522.32 ·
- Ollama · IQ4_XS Decode 224.73 · Prefill 806.05 ·
- Ollama · Q5_K_S Decode 182.89 · Prefill 696.63 ·
- Strata · Q5_K_S Decode 276.86 · Prefill 910.66 ·
Core figures
- Decode (avg)
- 152.59 tok/s
- Prefill (avg)
- 801.24 tok/s
- TTFT (avg)
- 0.81 s
- VRAM (avg)
- 23.84 GB
- MTP acceptance rate
- —
- TTFB
- 1.22 GB
- Power draw
- 295.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- Q8_0
- Framework
- vLLM
- Version
- v0.44
- Context length
- 4096 tokens
- Batch size
- 16
- GPU layers
- 999
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 5090
- Nominal VRAM
- 32 GB
- Measured VRAM (avg)
- 23.84 GB
- OS
- Windows 11 23H2
- Driver
- 570.86
- CUDA
- 12.8
- Power draw
- 295.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.44 · Windows 11 23H2 · CUDA 12.8 · 4096 ctx
152.59 tok/s
Decode
801.24 tok/s
Prefill
0.81 s
TTFT
23.84 GB
VRAM
—
MTP
295.9 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=13 running model_id=52 at Q8_0