← Back to community benchmarks
gemma-4-E2B-Heretic-Uncensored
Performance
1k
tokens
533.1
PP tok/s
36.1
TG tok/s
1921
TTFT (ms)
2.9
Peak mem (GB)
Hardware
Chip
M1 (8c)
Memory
8 GB
GPU Cores
8
Software
oMLX
v0.3.6
macOS
macOS 15.7.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 533.1 | 36.1 | 2.9 GB | current |
| 4k | 732.9 | 34.6 | 3.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 36.1 | 1.00× |
| 2× | 51.7 | 1.43× |
| 4× | 55.7 | 1.54× |