← Back to community benchmarks
gemma-4-26b-a4b-it-mxfp8
Performance
64k
tokens
1,222
PP tok/s
32.3
TG tok/s
53635
TTFT (ms)
28.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.10
macOS
macOS 26.5
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 64k | 1,222 | 32.3 | 28.5 GB | current |
| 128k | 822.8 | 24.7 | 33.5 GB | view |