Back to search results
Qwen3.5-9B · Q3_K_L
Apple M5 Pro64GBvLLM v0.38L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-9B (Q3_K_L) on Apple M5 Pro with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
145.87 tok/s
Decode
Decode speed
596.68 tok/s
Prefill
Prefill speed
2.39 s
TTFT
Time to first token
15.71 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- vLLM · Q3_K_L (current)Decode 145.87 · Prefill 596.68 ·
- vLLM · Q3_K_S Decode 149.44 · Prefill 576.02 ·
Core figures
- Decode (avg)
- 145.87 tok/s
- Prefill (avg)
- 596.68 tok/s
- TTFT (avg)
- 2.39 s
- VRAM (avg)
- 15.71 GB
- MTP acceptance rate
- —
- TTFB
- 1.17 GB
- Power draw
- 38.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-9B
- Quantization
- Q3_K_L
- Framework
- vLLM
- Version
- v0.38
- Context length
- 8192 tokens
- Batch size
- 32
- 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 M5 Pro
- Nominal VRAM
- 64 GB
- Measured VRAM (avg)
- 15.71 GB
- OS
- macOS 15.0
- Driver
- Apple M5 Pro
- CUDA
- N/A
- Power draw
- 38.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.38 · macOS 15.0 · CUDA N/A · 8192 ctx
145.87 tok/s
Decode
596.68 tok/s
Prefill
2.39 s
TTFT
15.71 GB
VRAM
—
MTP
38.3 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=27 running model_id=49 at Q3_K_L