Back to search results
Qwen2.5-0.5B-Instruct · Q3_K_L
Apple M2 ProvLLM v0.24L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (Q3_K_L) on Apple M2 Pro with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
248.22 tok/s
Decode
Decode speed
810.72 tok/s
Prefill
Prefill speed
0.92 s
TTFT
Time to first token
2.86 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · Q3_K_L (current)Decode 248.22 · Prefill 810.72 ·
- Ollama · Q5_K_S Decode 165.81 · Prefill 551.58 ·
- Ollama · Q8_0 Decode 140.52 · Prefill 749.46 ·
Core figures
- Decode (avg)
- 248.22 tok/s
- Prefill (avg)
- 810.72 tok/s
- TTFT (avg)
- 0.92 s
- VRAM (avg)
- 2.86 GB
- MTP acceptance rate
- —
- TTFB
- 1.99 GB
- Power draw
- 21.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-0.5B-Instruct
- Quantization
- Q3_K_L
- Framework
- vLLM
- Version
- v0.24
- Context length
- 8192 tokens
- Batch size
- 16
- 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
- Apple M2 Pro
- Measured VRAM (avg)
- 2.86 GB
- OS
- macOS 15.0
- Driver
- Apple M2 Pro
- CUDA
- N/A
- Power draw
- 21.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.24 · macOS 15.0 · CUDA N/A · 8192 ctx
248.22 tok/s
Decode
810.72 tok/s
Prefill
0.92 s
TTFT
2.86 GB
VRAM
—
MTP
21.8 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=102 running model_id=59 at Q3_K_L