← Back to community benchmarks
gemma-4-26B-A4B-it-heretic
Performance
16k
tokens
509.7
PP tok/s
40.4
TG tok/s
32144
TTFT (ms)
15.2
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
64 GB
GPU Cores
16
Software
oMLX
v0.3.4
macOS
macOS 26.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 4k | 440.1 | 51.9 | 14.7 GB | view |
| 16k | 509.7 | 40.4 | 15.2 GB | current |