← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
894.6
PP tok/s
37.3
TG tok/s
4578
TTFT (ms)
14.7
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.5
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 774.6 | 39.3 | 14.2 GB | view |
| 4k | 894.6 | 37.3 | 14.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 39.3 | 1.00× |
| 2× | 59.5 | 1.51× |
| 4× | 71.3 | 1.81× |