← Back to community benchmarks
gemma-4-E2B-it-oQ8
Performance
16k
tokens
467.6
PP tok/s
7.9
TG tok/s
35039
TTFT (ms)
6.2
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,597 | 27.1 | 6.0 GB | view |
| 4k | 941.3 | 25.6 | 6.1 GB | view |
| 8k | 772.6 | 14.5 | 6.1 GB | view |
| 16k | 467.6 | 7.9 | 6.2 GB | current |
| 32k | 458.1 | 18.7 | 6.5 GB | view |
| 64k | 697.0 | 16.5 | 7.3 GB | view |
| 128k | 463.4 | 11.0 | 7.8 GB | view |
| 195k | 339.5 | 8.4 | 9.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 27.1 | 1.00× |
| 2× | 33.7 | 1.24× |
| 4× | 43.3 | 1.60× |
| 8× | 64.3 | 2.37× |