Back to search results
Qwen3.5-9B · IQ1_S
Apple M1Strata v0.35L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-9B (IQ1_S) on Apple M1 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
96.89 tok/s
Decode
Decode speed
527.4 tok/s
Prefill
Prefill speed
2.49 s
TTFT
Time to first token
10.04 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 · Q3_K_M Decode 51.89 · Prefill 170.87 ·
- Strata · IQ1_S (current)Decode 96.89 · Prefill 527.4 ·
Core figures
- Decode (avg)
- 96.89 tok/s
- Prefill (avg)
- 527.4 tok/s
- TTFT (avg)
- 2.49 s
- VRAM (avg)
- 10.04 GB
- MTP acceptance rate
- 0.72
- TTFB
- 0.78 GB
- Power draw
- 26.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-9B
- Quantization
- IQ1_S
- Framework
- Strata
- Version
- v0.35
- Context length
- 32768 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 M1
- Measured VRAM (avg)
- 10.04 GB
- OS
- macOS 15.0
- Driver
- Apple M1
- CUDA
- N/A
- Power draw
- 26.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.35 · macOS 15.0 · CUDA N/A · 32768 ctx
96.89 tok/s
Decode
527.4 tok/s
Prefill
2.49 s
TTFT
10.04 GB
VRAM
0.72
MTP
26.8 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=99 running model_id=49 at IQ1_S