← Back to community benchmarks
gemma-4-E2B-it-uncensored-heretic-ara4bit-mixed_4_6
Performance
1k
tokens
2,264
PP tok/s
56.4
TG tok/s
452
TTFT (ms)
4.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,264 | 56.4 | 4.5 GB | current |
| 4k | 2,276 | 54.4 | 4.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 56.4 | 1.00× |
| 2× | 108.0 | 1.91× |
| 4× | 133.4 | 2.37× |