← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
35.9
PP tok/s
4.6
TG tok/s
114103
TTFT (ms)
14.7
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 21.8 | 3.6 | 14.2 GB | view |
| 4k | 35.9 | 4.6 | 14.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 3.6 | 1.00× |
| 2× | 8.2 | 2.28× |
| 4× | 7.8 | 2.17× |