← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
866.2
PP tok/s
41.6
TG tok/s
1182
TTFT (ms)
14.2
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 866.2 | 41.6 | 14.2 GB | current |
| 4k | 901.7 | 39.5 | 14.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 41.6 | 1.00× |
| 2× | 62.4 | 1.50× |
| 4× | 70.8 | 1.70× |