← Back to community benchmarks
gemma-4-26B-A4B-it-heretic
Performance
64k
tokens
427.2
PP tok/s
36.1
TG tok/s
153412
TTFT (ms)
17.7
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 32k | 513.9 | 46.1 | 16.0 GB | view |
| 64k | 427.2 | 36.1 | 17.7 GB | current |