← Back to community benchmarks
gemma-4-26B-A4B-it5bit
Performance
32k
tokens
198.6
PP tok/s
17.6
TG tok/s
164996
TTFT (ms)
18.9
Peak mem (GB)
Hardware
Chip
M1 Pro (14c)
Memory
32 GB
GPU Cores
14
Software
oMLX
v0.3.9rc1
macOS
macOS 26.5
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 32k | 198.6 | 17.6 | 18.9 GB | current |
| 64k | 173.5 | 12.6 | 21.4 GB | view |