Back to search results
Qwen2.5-Omni-3B · Q6_K
NVIDIA RTX 308010GBStrata v0.31L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (Q6_K) on NVIDIA RTX 3080 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
102.47 tok/s
Decode
Decode speed
544.89 tok/s
Prefill
Prefill speed
1.29 s
TTFT
Time to first token
8.4 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- Ollama · IQ2_M Decode 129.13 · Prefill 676.38 ·
- Strata · Q6_K (current)Decode 102.47 · Prefill 544.89 ·
Core figures
- Decode (avg)
- 102.47 tok/s
- Prefill (avg)
- 544.89 tok/s
- TTFT (avg)
- 1.29 s
- VRAM (avg)
- 8.4 GB
- MTP acceptance rate
- 0.46
- TTFB
- 0.82 GB
- Power draw
- 260.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-Omni-3B
- Quantization
- Q6_K
- Framework
- Strata
- Version
- v0.31
- Context length
- 16384 tokens
- Batch size
- 1024
- GPU layers
- 5
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 3080
- Nominal VRAM
- 10 GB
- Measured VRAM (avg)
- 8.4 GB
- OS
- macOS 15.0
- Driver
- 565.57
- CUDA
- 12.6
- Power draw
- 260.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.31 · macOS 15.0 · CUDA 12.6 · 16384 ctx
102.47 tok/s
Decode
544.89 tok/s
Prefill
1.29 s
TTFT
8.4 GB
VRAM
0.46
MTP
260.5 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=44 running model_id=60 at Q6_K