← Back to community benchmarks
gemma-4-26B-A4B-it-oQ4
Performance
32k
tokens
541.7
PP tok/s
37.3
TG tok/s
60486
TTFT (ms)
16.1
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
32 GB
GPU Cores
32
Software
oMLX
v0.3.9.dev2
macOS
macOS 15.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 32k | 541.7 | 37.3 | 16.1 GB | current |
| 64k | 401.6 | 24.1 | 18.7 GB | view |