← Back to community benchmarks
gemma-4-26B-A4B-it-uncensored-oQ8
Performance
64k
tokens
2,207
PP tok/s
46.6
TG tok/s
29697
TTFT (ms)
29.2
Peak mem (GB)
Hardware
Chip
M5 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 | 2,207 | 46.6 | 29.2 GB | current |
| 195k | 988.9 | 26.9 | 37.9 GB | view |