← Back to community benchmarks
gemma-4-E4B-it-Claude-Opus-4.5-HERETIC-UNCENSORED-Thinking-oQ4
Performance
4k
tokens
495.3
PP tok/s
42.9
TG tok/s
8270
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
16 GB
GPU Cores
16
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 452.1 | 46.1 | 4.8 GB | view |
| 4k | 495.3 | 42.9 | 4.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 46.1 | 1.00× |
| 2× | 55.8 | 1.21× |
| 4× | 60.7 | 1.32× |