← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
610.6
PP tok/s
30.7
TG tok/s
6708
TTFT (ms)
14.9
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 542.9 | 32.1 | 14.2 GB | view |
| 4k | 610.6 | 30.7 | 14.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.1 | 1.00× |
| 2× | 39.3 | 1.22× |
| 4× | 44.9 | 1.40× |