Back to search results
Qwen2.5-Omni-3B · Q5_K_S
Qualcomm Snapdragon X ElitevLLM v0.47L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (Q5_K_S) on Qualcomm Snapdragon X Elite with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
65.67 tok/s
Decode
Decode speed
300.03 tok/s
Prefill
Prefill speed
1.24 s
TTFT
Time to first token
7.77 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · IQ2_XS Decode 103.58 · Prefill 468.29 ·
- vLLM · Q5_K_S (current)Decode 65.67 · Prefill 300.03 ·
- Ollama · Q2_K Decode 89.58 · Prefill 387.16 ·
- Ollama · Q3_K_S Decode 76.04 · Prefill 366.79 ·
Core figures
- Decode (avg)
- 65.67 tok/s
- Prefill (avg)
- 300.03 tok/s
- TTFT (avg)
- 1.24 s
- VRAM (avg)
- 7.77 GB
- MTP acceptance rate
- —
- TTFB
- 0.53 GB
- Power draw
- 17.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-Omni-3B
- Quantization
- Q5_K_S
- Framework
- vLLM
- Version
- v0.47
- Context length
- 8192 tokens
- Batch size
- 32
- GPU layers
- 999
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Qualcomm Snapdragon X Elite
- Measured VRAM (avg)
- 7.77 GB
- OS
- Windows 11 23H2
- Driver
- Qualcomm Adreno 7.0
- CUDA
- N/A
- Power draw
- 17.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.47 · Windows 11 23H2 · CUDA N/A · 8192 ctx
65.67 tok/s
Decode
300.03 tok/s
Prefill
1.24 s
TTFT
7.77 GB
VRAM
—
MTP
17.9 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=104 running model_id=60 at Q5_K_S