Back to search results
Qwen3.5-9B · Q5_K_M
Apple M5 Max128GBvLLM v0.26L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-9B (Q5_K_M) on Apple M5 Max with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
148.01 tok/s
Decode
Decode speed
738.05 tok/s
Prefill
Prefill speed
1.62 s
TTFT
Time to first token
19.68 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- vLLM · IQ3_S Decode 222.48 · Prefill 1168.2 ·
- vLLM · Q5_K_S Decode 163.05 · Prefill 700.99 ·
- Strata · Q3_K_M Decode 284.27 · Prefill 948.35 ·
- vLLM · Q5_K_M (current)Decode 148.01 · Prefill 738.05 ·
Core figures
- Decode (avg)
- 148.01 tok/s
- Prefill (avg)
- 738.05 tok/s
- TTFT (avg)
- 1.62 s
- VRAM (avg)
- 19.68 GB
- MTP acceptance rate
- —
- TTFB
- 1.18 GB
- Power draw
- 115 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-9B
- Quantization
- Q5_K_M
- Framework
- vLLM
- Version
- v0.26
- 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 M5 Max
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 19.68 GB
- OS
- macOS 15.0
- Driver
- Apple M5 Max
- CUDA
- N/A
- Power draw
- 115 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.26 · macOS 15.0 · CUDA N/A · 8192 ctx
148.01 tok/s
Decode
738.05 tok/s
Prefill
1.62 s
TTFT
19.68 GB
VRAM
—
MTP
115 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=28 running model_id=49 at Q5_K_M