Back to search results
Qwen3.5-9B · FP16
Apple M1 MaxStrata v0.33L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-9B (FP16) on Apple M1 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
50.07 tok/s
Decode
Decode speed
196.15 tok/s
Prefill
Prefill speed
2.13 s
TTFT
Time to first token
37.06 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- llama.cpp · Q5_K_M Decode 65.43 · Prefill 334.37 ·
- Strata · FP16 (current)Decode 50.07 · Prefill 196.15 ·
- Strata · Q5_K_M Decode 86.88 · Prefill 306.63 ·
Core figures
- Decode (avg)
- 50.07 tok/s
- Prefill (avg)
- 196.15 tok/s
- TTFT (avg)
- 2.13 s
- VRAM (avg)
- 37.06 GB
- MTP acceptance rate
- 0.69
- TTFB
- 0.4 GB
- Power draw
- 59.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-9B
- Quantization
- FP16
- Framework
- Strata
- Version
- v0.33
- Context length
- 16384 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 M1 Max
- Measured VRAM (avg)
- 37.06 GB
- OS
- macOS 15.0
- Driver
- Apple M1 Max
- CUDA
- N/A
- Power draw
- 59.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.33 · macOS 15.0 · CUDA N/A · 16384 ctx
50.07 tok/s
Decode
196.15 tok/s
Prefill
2.13 s
TTFT
37.06 GB
VRAM
0.69
MTP
59.2 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=101 running model_id=49 at FP16