Back to search results
Qwen2.5-0.5B-Instruct · IQ2_XS
NVIDIA RTX 408016GBvLLM v0.50L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (IQ2_XS) on NVIDIA RTX 4080 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
372.57 tok/s
Decode
Decode speed
1,858.32 tok/s
Prefill
Prefill speed
0.28 s
TTFT
Time to first token
2.6 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- vLLM · IQ2_XS (current)Decode 372.57 · Prefill 1858.32 ·
Core figures
- Decode (avg)
- 372.57 tok/s
- Prefill (avg)
- 1,858.32 tok/s
- TTFT (avg)
- 0.28 s
- VRAM (avg)
- 2.6 GB
- MTP acceptance rate
- —
- TTFB
- 2.98 GB
- Power draw
- 302.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-0.5B-Instruct
- Quantization
- IQ2_XS
- Framework
- vLLM
- Version
- v0.50
- Context length
- 4096 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 4080
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 2.6 GB
- OS
- Ubuntu 22.04
- Driver
- 565.57
- CUDA
- 12.4
- Power draw
- 302.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.50 · Ubuntu 22.04 · CUDA 12.4 · 4096 ctx
372.57 tok/s
Decode
1,858.32 tok/s
Prefill
0.28 s
TTFT
2.6 GB
VRAM
—
MTP
302.2 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=41 running model_id=59 at IQ2_XS