Back to search results
Qwen2.5-Omni-3B · IQ1_S
Apple M2 ProvLLM v0.54L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (IQ1_S) on Apple M2 Pro with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
161.76 tok/s
Decode
Decode speed
837.8 tok/s
Prefill
Prefill speed
2.25 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
2 days ago
Last verified
Performance
- vLLM · IQ1_S (current)Decode 161.76 · Prefill 837.8 ·
- Ollama · IQ2_XS Decode 130.3 · Prefill 686.33 ·
- Ollama · Q3_K_L Decode 100.83 · Prefill 364.74 ·
Core figures
- Decode (avg)
- 161.76 tok/s
- Prefill (avg)
- 837.8 tok/s
- TTFT (avg)
- 2.25 s
- VRAM (avg)
- 4.75 GB
- MTP acceptance rate
- —
- TTFB
- 1.29 GB
- Power draw
- 44.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-Omni-3B
- Quantization
- IQ1_S
- Framework
- vLLM
- Version
- v0.54
- Context length
- 8192 tokens
- Batch size
- 16
- GPU layers
- 999
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M2 Pro
- Measured VRAM (avg)
- 4.75 GB
- OS
- macOS 15.0
- Driver
- Apple M2 Pro
- CUDA
- N/A
- Power draw
- 44.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.54 · macOS 15.0 · CUDA N/A · 8192 ctx
161.76 tok/s
Decode
837.8 tok/s
Prefill
2.25 s
TTFT
4.75 GB
VRAM
—
MTP
44.2 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=102 running model_id=60 at IQ1_S