Back to search results
Qwen3.5-0.8B · Q2_K
Apple M1Strata v0.22L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q2_K) on Apple M1 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
231.36 tok/s
Decode
Decode speed
1,029.89 tok/s
Prefill
Prefill speed
1.36 s
TTFT
Time to first token
3.02 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · Q4_K_S Decode 132.87 · Prefill 708.61 ·
- Strata · Q2_K (current)Decode 231.36 · Prefill 1029.89 ·
Core figures
- Decode (avg)
- 231.36 tok/s
- Prefill (avg)
- 1,029.89 tok/s
- TTFT (avg)
- 1.36 s
- VRAM (avg)
- 3.02 GB
- MTP acceptance rate
- 0.6
- TTFB
- 1.85 GB
- Power draw
- 53.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- Q2_K
- Framework
- Strata
- Version
- v0.22
- Context length
- 2048 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
- Measured VRAM (avg)
- 3.02 GB
- OS
- macOS 15.0
- Driver
- Apple M1
- CUDA
- N/A
- Power draw
- 53.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.22 · macOS 15.0 · CUDA N/A · 2048 ctx
231.36 tok/s
Decode
1,029.89 tok/s
Prefill
1.36 s
TTFT
3.02 GB
VRAM
0.6
MTP
53.5 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=99 running model_id=51 at Q2_K