Back to search results
Qwen2.5-Omni-3B · Q3_K_S
Apple M4 Pro64GBvLLM v0.23L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (Q3_K_S) on Apple M4 Pro with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
184.21 tok/s
Decode
Decode speed
1,008.8 tok/s
Prefill
Prefill speed
2.39 s
TTFT
Time to first token
6.2 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- vLLM · IQ4_XS Decode 172.49 · Prefill 661.58 ·
- vLLM · Q3_K_S (current)Decode 184.21 · Prefill 1008.8 ·
- Ollama · Q4_K_S Decode 154.32 · Prefill 813.63 ·
- Ollama · Q5_K_M Decode 114.09 · Prefill 438.42 ·
Core figures
- Decode (avg)
- 184.21 tok/s
- Prefill (avg)
- 1,008.8 tok/s
- TTFT (avg)
- 2.39 s
- VRAM (avg)
- 6.2 GB
- MTP acceptance rate
- —
- TTFB
- 1.47 GB
- Power draw
- 80.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-Omni-3B
- Quantization
- Q3_K_S
- Framework
- vLLM
- Version
- v0.23
- Context length
- 2048 tokens
- Batch size
- 8
- 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 M4 Pro
- Nominal VRAM
- 64 GB
- Measured VRAM (avg)
- 6.2 GB
- OS
- macOS 15.0
- Driver
- Apple M4 Pro
- CUDA
- N/A
- Power draw
- 80.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.23 · macOS 15.0 · CUDA N/A · 2048 ctx
184.21 tok/s
Decode
1,008.8 tok/s
Prefill
2.39 s
TTFT
6.2 GB
VRAM
—
MTP
80.9 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=25 running model_id=60 at Q3_K_S