Back to search results
Qwen3.5-27B · Q4_K_M
Apple M2 UltraStrata v0.54L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-27B (Q4_K_M) on Apple M2 Ultra with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
113.85 tok/s
Decode
Decode speed
614.05 tok/s
Prefill
Prefill speed
0.28 s
TTFT
Time to first token
48.59 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- Ollama · Q8_0 Decode 49.84 · Prefill 240.92 ·
- Strata · Q4_K_M (current)Decode 113.85 · Prefill 614.05 ·
Core figures
- Decode (avg)
- 113.85 tok/s
- Prefill (avg)
- 614.05 tok/s
- TTFT (avg)
- 0.28 s
- VRAM (avg)
- 48.59 GB
- MTP acceptance rate
- 0.77
- TTFB
- 0.91 GB
- Power draw
- 18.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-27B
- Quantization
- Q4_K_M
- Framework
- Strata
- Version
- v0.54
- Context length
- 4096 tokens
- Batch size
- 512
- 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 M2 Ultra
- Measured VRAM (avg)
- 48.59 GB
- OS
- macOS 15.0
- Driver
- Apple M2 Ultra
- CUDA
- N/A
- Power draw
- 18.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.54 · macOS 15.0 · CUDA N/A · 4096 ctx
113.85 tok/s
Decode
614.05 tok/s
Prefill
0.28 s
TTFT
48.59 GB
VRAM
0.77
MTP
18.1 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=103 running model_id=50 at Q4_K_M