← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
369.9
PP tok/s
34.6
TG tok/s
2768
TTFT (ms)
14.2
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 369.9 | 34.6 | 14.2 GB | current |
| 4k | 377.2 | 33.3 | 14.9 GB | view |
| 8k | 369.1 | 32.1 | 15.0 GB | view |
| 16k | 339.2 | 29.3 | 15.5 GB | view |
| 32k | 290.5 | 24.6 | 16.4 GB | view |
| 64k | 234.1 | 16.4 | 18.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 34.6 | 1.00× |
| 2× | 50.1 | 1.45× |