Back to search results
gemma-4-E2B-it · Q3_K_L
Apple M2 UltraStrata v0.43L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-E2B-it (Q3_K_L) on Apple M2 Ultra with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
291.87 tok/s
Decode
Decode speed
1,161.97 tok/s
Prefill
Prefill speed
1.53 s
TTFT
Time to first token
5.12 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 · IQ2_XS Decode 255.2 · Prefill 1294.22 ·
- llama.cpp · Q3_K_S Decode 222.24 · Prefill 799.86 ·
- Strata · Q3_K_L (current)Decode 291.87 · Prefill 1161.97 ·
Core figures
- Decode (avg)
- 291.87 tok/s
- Prefill (avg)
- 1,161.97 tok/s
- TTFT (avg)
- 1.53 s
- VRAM (avg)
- 5.12 GB
- MTP acceptance rate
- 0.45
- TTFB
- 2.33 GB
- Power draw
- 73.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-E2B-it
- Quantization
- Q3_K_L
- Framework
- Strata
- Version
- v0.43
- Context length
- 2048 tokens
- Batch size
- 1024
- 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 M2 Ultra
- Measured VRAM (avg)
- 5.12 GB
- OS
- macOS 15.0
- Driver
- Apple M2 Ultra
- CUDA
- N/A
- Power draw
- 73.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.43 · macOS 15.0 · CUDA N/A · 2048 ctx
291.87 tok/s
Decode
1,161.97 tok/s
Prefill
1.53 s
TTFT
5.12 GB
VRAM
0.45
MTP
73.9 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=103 running model_id=66 at Q3_K_L