Back to search results
Qwen2.5-Omni-3B · Q5_K_M
Apple M1 ProvLLM v0.50L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (Q5_K_M) on Apple M1 Pro with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
93.64 tok/s
Decode
Decode speed
442.19 tok/s
Prefill
Prefill speed
0.47 s
TTFT
Time to first token
7.96 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · Q5_K_M (current)Decode 93.64 · Prefill 442.19 ·
- vLLM · Q5_K_S Decode 89.03 · Prefill 302.53 ·
- Ollama · IQ1_S Decode 134.09 · Prefill 528.37 ·
- Ollama · Q2_K Decode 116.73 · Prefill 402.44 ·
Core figures
- Decode (avg)
- 93.64 tok/s
- Prefill (avg)
- 442.19 tok/s
- TTFT (avg)
- 0.47 s
- VRAM (avg)
- 7.96 GB
- MTP acceptance rate
- —
- TTFB
- 0.75 GB
- Power draw
- 24.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-Omni-3B
- Quantization
- Q5_K_M
- Framework
- vLLM
- Version
- v0.50
- 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 M1 Pro
- Measured VRAM (avg)
- 7.96 GB
- OS
- macOS 15.0
- Driver
- Apple M1 Pro
- CUDA
- N/A
- Power draw
- 24.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.50 · macOS 15.0 · CUDA N/A · 8192 ctx
93.64 tok/s
Decode
442.19 tok/s
Prefill
0.47 s
TTFT
7.96 GB
VRAM
—
MTP
24.3 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=100 running model_id=60 at Q5_K_M