Back to search results
gemma-4-E2B-it · IQ1_S
Apple M1 MaxStrata v0.37L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-E2B-it (IQ1_S) on Apple M1 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
324.26 tok/s
Decode
Decode speed
1,495.83 tok/s
Prefill
Prefill speed
2.12 s
TTFT
Time to first token
3.86 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · Q3_K_S Decode 189.55 · Prefill 943.94 ·
- vLLM · Q8_0 Decode 98.82 · Prefill 455.48 ·
- Strata · IQ1_S (current)Decode 324.26 · Prefill 1495.83 ·
Core figures
- Decode (avg)
- 324.26 tok/s
- Prefill (avg)
- 1,495.83 tok/s
- TTFT (avg)
- 2.12 s
- VRAM (avg)
- 3.86 GB
- MTP acceptance rate
- 0.67
- TTFB
- 2.59 GB
- Power draw
- 52.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-E2B-it
- Quantization
- IQ1_S
- Framework
- Strata
- Version
- v0.37
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 15
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M1 Max
- Measured VRAM (avg)
- 3.86 GB
- OS
- macOS 15.0
- Driver
- Apple M1 Max
- CUDA
- N/A
- Power draw
- 52.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.37 · macOS 15.0 · CUDA N/A · 32768 ctx
324.26 tok/s
Decode
1,495.83 tok/s
Prefill
2.12 s
TTFT
3.86 GB
VRAM
0.67
MTP
52.8 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=101 running model_id=66 at IQ1_S