← Back to community benchmarks
gemma-4-E4B-it-Claude-Opus-4.5-HERETIC-UNCENSORED-Thinking-oQ3
Performance
1k
tokens
696.2
PP tok/s
54.1
TG tok/s
1471
TTFT (ms)
3.9
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
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 696.2 | 54.1 | 3.9 GB | current |
| 4k | 807.9 | 51.0 | 4.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.1 | 1.00× |
| 2× | 66.4 | 1.23× |
| 4× | 73.4 | 1.36× |