Back to search results
Qwen3.5-9B · IQ2_M
Apple M4 Pro64GBStrata v0.26L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-9B (IQ2_M) on Apple M4 Pro with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
177.44 tok/s
Decode
Decode speed
840.26 tok/s
Prefill
Prefill speed
0.72 s
TTFT
Time to first token
11.93 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- Strata · IQ2_M (current)Decode 177.44 · Prefill 840.26 ·
Core figures
- Decode (avg)
- 177.44 tok/s
- Prefill (avg)
- 840.26 tok/s
- TTFT (avg)
- 0.72 s
- VRAM (avg)
- 11.93 GB
- MTP acceptance rate
- 0.72
- TTFB
- 1.42 GB
- Power draw
- 83.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-9B
- Quantization
- IQ2_M
- Framework
- Strata
- Version
- v0.26
- Context length
- 16384 tokens
- Batch size
- 1024
- GPU layers
- 5
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M4 Pro
- Nominal VRAM
- 64 GB
- Measured VRAM (avg)
- 11.93 GB
- OS
- macOS 15.0
- Driver
- Apple M4 Pro
- CUDA
- N/A
- Power draw
- 83.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.26 · macOS 15.0 · CUDA N/A · 16384 ctx
177.44 tok/s
Decode
840.26 tok/s
Prefill
0.72 s
TTFT
11.93 GB
VRAM
0.72
MTP
83.7 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=25 running model_id=49 at IQ2_M