← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
715.3
PP tok/s
37.9
TG tok/s
1432
TTFT (ms)
14.2
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 715.3 | 37.9 | 14.2 GB | current |
| 4k | 946.7 | 38.5 | 14.7 GB | view |
| 8k | 1,025 | 33.1 | 14.8 GB | view |
| 32k | 854.9 | 19.1 | 15.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 37.9 | 1.00× |
| 2× | 83.0 | 2.19× |
| 4× | 163.2 | 4.31× |