Back to search results
Qwen2.5-Omni-3B · IQ3_S
NVIDIA RTX 509032GBStrata v0.30L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (IQ3_S) on NVIDIA RTX 5090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
359.64 tok/s
Decode
Decode speed
1,323.17 tok/s
Prefill
Prefill speed
0.17 s
TTFT
Time to first token
6.26 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- llama.cpp · IQ4_XS Decode 375.39 · Prefill 1839.32 ·
- llama.cpp · Q6_K Decode 277.82 · Prefill 934.6 ·
- Strata · FP16 Decode 238.76 · Prefill 798.02 ·
- Strata · IQ3_S (current)Decode 359.64 · Prefill 1323.17 ·
- llama.cpp · Q8_0 Decode 436.8 · Prefill 3276 ·
- llama.cpp · Q5_K_M Decode 635.3 · Prefill 4764.8 ·
- llama.cpp · Q4_K_M Decode 776.5 · Prefill 5823.8 ·
Core figures
- Decode (avg)
- 359.64 tok/s
- Prefill (avg)
- 1,323.17 tok/s
- TTFT (avg)
- 0.17 s
- VRAM (avg)
- 6.26 GB
- MTP acceptance rate
- 0.71
- TTFB
- 2.88 GB
- Power draw
- 323.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-Omni-3B
- Quantization
- IQ3_S
- Framework
- Strata
- Version
- v0.30
- Context length
- 16384 tokens
- Batch size
- 256
- 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 5090
- Nominal VRAM
- 32 GB
- Measured VRAM (avg)
- 6.26 GB
- OS
- Ubuntu 24.04
- Driver
- 565.57
- CUDA
- 12.8
- Power draw
- 323.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.30 · Ubuntu 24.04 · CUDA 12.8 · 16384 ctx
359.64 tok/s
Decode
1,323.17 tok/s
Prefill
0.17 s
TTFT
6.26 GB
VRAM
0.71
MTP
323.3 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=13 running model_id=60 at IQ3_S