← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
249.2
PP tok/s
33.7
TG tok/s
16436
TTFT (ms)
14.7
Peak mem (GB)
Hardware
Chip
M1 Pro (16c)
Memory
32 GB
GPU Cores
16
Software
oMLX
v0.3.4
macOS
macOS 15.7.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 235.9 | 36.5 | 14.2 GB | view |
| 4k | 249.2 | 33.7 | 14.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 36.5 | 1.00× |
| 2× | 44.4 | 1.22× |
| 4× | 49.2 | 1.35× |