Back to search results
Qwen3.8-9B · Q2_K
NVIDIA RTX 508016GBvLLM v0.50L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (Q2_K) on NVIDIA RTX 5080 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
238.4 tok/s
Decode
Decode speed
951.3 tok/s
Prefill
Prefill speed
2.01 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
17 days ago
Last verified
Performance
- llama.cpp · IQ3_S Decode 200.28 · Prefill 716.67 ·
- vLLM · Q2_K (current)Decode 238.4 · Prefill 951.3 ·
- vLLM · Q4_K_M Decode 152.58 · Prefill 685.84 ·
- Strata · IQ2_M Decode 294.71 · Prefill 1507.15 ·
- Strata · IQ3_XS Decode 265.22 · Prefill 1010.61 ·
- llama.cpp · IQ4_XS Decode 97.14 · Prefill 496.38 ·
- llama.cpp · Q3_K_M Decode 108.92 · Prefill 455.22 ·
- vLLM · IQ2_M Decode 131.31 · Prefill 559.09 ·
Core figures
- Decode (avg)
- 238.4 tok/s
- Prefill (avg)
- 951.3 tok/s
- TTFT (avg)
- 2.01 s
- VRAM (avg)
- 12.5 GB
- MTP acceptance rate
- —
- TTFB
- 1.91 GB
- Power draw
- 344.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- Q2_K
- Framework
- vLLM
- Version
- v0.50
- Context length
- 2048 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 5080
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 12.5 GB
- OS
- Windows 11 23H2
- Driver
- 570.86
- CUDA
- 12.8
- Power draw
- 344.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.50 · Windows 11 23H2 · CUDA 12.8 · 2048 ctx
238.4 tok/s
Decode
951.3 tok/s
Prefill
2.01 s
TTFT
12.5 GB
VRAM
—
MTP
344.8 W
Power draw
L2 batch seed 2026-10-19: vLLM on hw_id=14 running model_id=52 at Q2_K