← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
366.7
PP tok/s
45.7
TG tok/s
11171
TTFT (ms)
14.9
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 332.6 | 48.0 | 14.3 GB | view |
| 4k | 366.7 | 45.7 | 14.9 GB | current |
| 8k | 371.3 | 43.0 | 15.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.0 | 1.00× |
| 2× | 57.4 | 1.20× |
| 4× | 70.5 | 1.47× |