← Back to community benchmarks
Gemma-4-26B-A4B-Heretic
Performance
64k
tokens
1,029
PP tok/s
36.5
TG tok/s
63714
TTFT (ms)
51.2
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
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 | |
|---|---|---|---|---|
| 64k | 1,029 | 36.5 | 51.2 GB | current |
| 128k | 753.2 | 28.3 | 54.8 GB | view |