Back to search results
Qwen2.5-Omni-3B · IQ2_XS
NVIDIA RTX 408016GBStrata v0.31L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (IQ2_XS) on NVIDIA RTX 4080 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
273.01 tok/s
Decode
Decode speed
1,309.97 tok/s
Prefill
Prefill speed
2.43 s
TTFT
Time to first token
5.12 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- Strata · IQ1_S Decode 264.72 · Prefill 1096.35 ·
- Strata · IQ2_XS (current)Decode 273.01 · Prefill 1309.97 ·
Core figures
- Decode (avg)
- 273.01 tok/s
- Prefill (avg)
- 1,309.97 tok/s
- TTFT (avg)
- 2.43 s
- VRAM (avg)
- 5.12 GB
- MTP acceptance rate
- 0.65
- TTFB
- 2.18 GB
- Power draw
- 301.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-Omni-3B
- Quantization
- IQ2_XS
- Framework
- Strata
- Version
- v0.31
- Context length
- 8192 tokens
- Batch size
- 1024
- GPU layers
- 5
- Flash Attention
- Off
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)
- 5.12 GB
- OS
- Ubuntu 24.04
- Driver
- 560.94
- CUDA
- 12.8
- Power draw
- 301.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.31 · Ubuntu 24.04 · CUDA 12.8 · 8192 ctx
273.01 tok/s
Decode
1,309.97 tok/s
Prefill
2.43 s
TTFT
5.12 GB
VRAM
0.65
MTP
301.8 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=41 running model_id=60 at IQ2_XS