Back to search results
Qwen2.5-0.5B-Instruct · Q4_K_S
Apple M2 UltravLLM v0.54L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (Q4_K_S) on Apple M2 Ultra with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
318.45 tok/s
Decode
Decode speed
1,454.37 tok/s
Prefill
Prefill speed
0.76 s
TTFT
Time to first token
2.92 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · Q4_K_S (current)Decode 318.45 · Prefill 1454.37 ·
- Ollama · Q2_K Decode 393.85 · Prefill 1387.41 ·
- Ollama · Q4_K_M Decode 265.57 · Prefill 1148.27 ·
Core figures
- Decode (avg)
- 318.45 tok/s
- Prefill (avg)
- 1,454.37 tok/s
- TTFT (avg)
- 0.76 s
- VRAM (avg)
- 2.92 GB
- MTP acceptance rate
- —
- TTFB
- 2.55 GB
- Power draw
- 45.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-0.5B-Instruct
- Quantization
- Q4_K_S
- Framework
- vLLM
- Version
- v0.54
- Context length
- 8192 tokens
- Batch size
- 32
- 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 Ultra
- Measured VRAM (avg)
- 2.92 GB
- OS
- macOS 15.0
- Driver
- Apple M2 Ultra
- CUDA
- N/A
- Power draw
- 45.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.54 · macOS 15.0 · CUDA N/A · 8192 ctx
318.45 tok/s
Decode
1,454.37 tok/s
Prefill
0.76 s
TTFT
2.92 GB
VRAM
—
MTP
45.8 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=103 running model_id=59 at Q4_K_S