← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
64k
tokens
519.3
PP tok/s
31.4
TG tok/s
126195
TTFT (ms)
29.2
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.3.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 672.8 | 45.7 | 25.8 GB | view |
| 4k | 729.4 | 44.1 | 26.4 GB | view |
| 64k | 519.3 | 31.4 | 29.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 45.7 | 1.00× |
| 2× | 57.3 | 1.25× |
| 4× | 83.7 | 1.83× |