Back to search results
Qwen2.5-Omni-3B · IQ1_S
NVIDIA RTX 408016GBStrata v0.42L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (IQ1_S) on NVIDIA RTX 4080 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
264.72 tok/s
Decode
Decode speed
1,096.35 tok/s
Prefill
Prefill speed
2.01 s
TTFT
Time to first token
4.75 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 (current)Decode 264.72 · Prefill 1096.35 ·
- Strata · IQ2_XS Decode 273.01 · Prefill 1309.97 ·
Core figures
- Decode (avg)
- 264.72 tok/s
- Prefill (avg)
- 1,096.35 tok/s
- TTFT (avg)
- 2.01 s
- VRAM (avg)
- 4.75 GB
- MTP acceptance rate
- 0.71
- TTFB
- 2.12 GB
- Power draw
- 292.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-Omni-3B
- Quantization
- IQ1_S
- Framework
- Strata
- Version
- v0.42
- Context length
- 8192 tokens
- Batch size
- 1024
- GPU layers
- 8
- 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)
- 4.75 GB
- OS
- Ubuntu 24.04
- Driver
- 560.94
- CUDA
- 12.4
- Power draw
- 292.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.42 · Ubuntu 24.04 · CUDA 12.4 · 8192 ctx
264.72 tok/s
Decode
1,096.35 tok/s
Prefill
2.01 s
TTFT
4.75 GB
VRAM
0.71
MTP
292.1 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=41 running model_id=60 at IQ1_S