Back to search results
Qwen3.5-9B · Q3_K_M
Apple M5 Max128GBStrata v0.25L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-9B (Q3_K_M) on Apple M5 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
284.27 tok/s
Decode
Decode speed
948.35 tok/s
Prefill
Prefill speed
0.47 s
TTFT
Time to first token
14.95 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 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 (current)Decode 284.27 · Prefill 948.35 ·
- vLLM · Q5_K_M Decode 148.01 · Prefill 738.05 ·
Core figures
- Decode (avg)
- 284.27 tok/s
- Prefill (avg)
- 948.35 tok/s
- TTFT (avg)
- 0.47 s
- VRAM (avg)
- 14.95 GB
- MTP acceptance rate
- 0.45
- TTFB
- 2.27 GB
- Power draw
- 264.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-9B
- Quantization
- Q3_K_M
- Framework
- Strata
- Version
- v0.25
- Context length
- 8192 tokens
- Batch size
- 256
- GPU layers
- 12
- 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)
- 14.95 GB
- OS
- macOS 15.0
- Driver
- 565.57
- CUDA
- 12.8
- Power draw
- 264.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.25 · macOS 15.0 · CUDA 12.8 · 8192 ctx
284.27 tok/s
Decode
948.35 tok/s
Prefill
0.47 s
TTFT
14.95 GB
VRAM
0.45
MTP
264.5 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=28 running model_id=49 at Q3_K_M