← Back to community benchmarks
gemma-4-E2B-it-oQ8
Performance
64k
tokens
1,072
PP tok/s
20.5
TG tok/s
61139
TTFT (ms)
7.3
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,818 | 32.2 | 6.0 GB | view |
| 4k | 1,919 | 30.9 | 6.1 GB | view |
| 8k | 1,853 | 29.3 | 6.1 GB | view |
| 16k | 1,713 | 26.8 | 6.2 GB | view |
| 32k | 1,452 | 24.8 | 6.5 GB | view |
| 64k | 1,072 | 20.5 | 7.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.2 | 1.00× |
| 2× | 60.8 | 1.89× |
| 4× | 89.6 | 2.78× |
| 8× | 115.6 | 3.59× |