Qwen3.5-9B · Q3_K_M

Apple M2 ProStrata v0.52L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-9B (Q3_K_M) on Apple M2 Pro with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

98.43 tok/s

Decode

Decode speed

413.44 tok/s

Prefill

Prefill speed

0.26 s

TTFT

Time to first token

14.95 GB

VRAM

VRAM usage

L2 Cross-framework verified

Measured runs

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

Ollama · Q3_K_L Decode 72.52 · Prefill 271.12 ·
Ollama · Q5_K_M Decode 52.96 · Prefill 269.51 ·
Strata · Q3_K_M (current)Decode 98.43 · Prefill 413.44 ·
Strata · Q5_K_S Decode 84.64 · Prefill 401.91 ·

Core figures

Decode (avg): 98.43 tok/s
Prefill (avg): 413.44 tok/s
TTFT (avg): 0.26 s
VRAM (avg): 14.95 GB
MTP acceptance rate: 0.54
TTFB: 0.79 GB
Power draw: 19.3 W

Configuration

Member-level fields are taken from the most recent run

Model: Qwen3.5-9B
Quantization: Q3_K_M
Framework: Strata
Version: v0.52
Context length: 8192 tokens
Batch size: 512
GPU layers: 8
Flash Attention: On

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU: Apple M2 Pro
Measured VRAM (avg): 14.95 GB
OS: macOS 15.0
Driver: Apple M2 Pro
CUDA: N/A
Power draw: 19.3 W

Sources & evidence

1 measured records in total, each traceable to its original source

L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-16
v0.52 · macOS 15.0 · CUDA N/A · 8192 ctx
98.43 tok/s
Decode
413.44 tok/s
Prefill
0.26 s
TTFT
14.95 GB
VRAM
0.54
MTP
19.3 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=102 running model_id=49 at Q3_K_M