Back to search results
Qwen3-4B · Q3_K_L
Apple M2 UltraStrata v0.26L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B (Q3_K_L) on Apple M2 Ultra with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
200.62 tok/s
Decode
Decode speed
720.62 tok/s
Prefill
Prefill speed
1.63 s
TTFT
Time to first token
8.15 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- Ollama · FP16 Decode 64.08 · Prefill 216.32 ·
- Ollama · IQ2_XS Decode 161.88 · Prefill 564.86 ·
- Strata · Q3_K_L (current)Decode 200.62 · Prefill 720.62 ·
- Strata · Q5_K_S Decode 162.1 · Prefill 686.85 ·
Core figures
- Decode (avg)
- 200.62 tok/s
- Prefill (avg)
- 720.62 tok/s
- TTFT (avg)
- 1.63 s
- VRAM (avg)
- 8.15 GB
- MTP acceptance rate
- 0.61
- TTFB
- 1.6 GB
- Power draw
- 51.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B
- Quantization
- Q3_K_L
- Framework
- Strata
- Version
- v0.26
- Context length
- 32768 tokens
- Batch size
- 1024
- 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 Ultra
- Measured VRAM (avg)
- 8.15 GB
- OS
- macOS 15.0
- Driver
- Apple M2 Ultra
- CUDA
- N/A
- Power draw
- 51.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.26 · macOS 15.0 · CUDA N/A · 32768 ctx
200.62 tok/s
Decode
720.62 tok/s
Prefill
1.63 s
TTFT
8.15 GB
VRAM
0.61
MTP
51.2 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=103 running model_id=54 at Q3_K_L