← Back to community benchmarks
gemma-4-E2B-Heretic-Uncensored
Performance
1k
tokens
1,314
PP tok/s
62.9
TG tok/s
779
TTFT (ms)
2.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,314 | 62.9 | 2.9 GB | current |
| 4k | 1,985 | 58.7 | 3.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 62.9 | 1.00× |
| 2× | 118.2 | 1.88× |
| 4× | 151.7 | 2.41× |