Back to search results
Qwen3.5-0.8B · IQ3_S
Apple M2 ProStrata v0.43L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ3_S) on Apple M2 Pro with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
271.19 tok/s
Decode
Decode speed
1,175.39 tok/s
Prefill
Prefill speed
2.06 s
TTFT
Time to first token
3.21 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- Ollama · Q3_K_M Decode 180.06 · Prefill 719.07 ·
- Strata · IQ3_S (current)Decode 271.19 · Prefill 1175.39 ·
- Strata · Q3_K_L Decode 271.73 · Prefill 1155.68 ·
Core figures
- Decode (avg)
- 271.19 tok/s
- Prefill (avg)
- 1,175.39 tok/s
- TTFT (avg)
- 2.06 s
- VRAM (avg)
- 3.21 GB
- MTP acceptance rate
- 0.77
- TTFB
- 2.17 GB
- Power draw
- 55.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- IQ3_S
- Framework
- Strata
- Version
- v0.43
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 15
- 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)
- 3.21 GB
- OS
- macOS 15.0
- Driver
- Apple M2 Pro
- CUDA
- N/A
- Power draw
- 55.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.43 · macOS 15.0 · CUDA N/A · 32768 ctx
271.19 tok/s
Decode
1,175.39 tok/s
Prefill
2.06 s
TTFT
3.21 GB
VRAM
0.77
MTP
55.3 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=102 running model_id=51 at IQ3_S