← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
989.0
PP tok/s
37.2
TG tok/s
4142
TTFT (ms)
15.4
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.1
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 948.9 | 38.7 | 15.0 GB | view |
| 4k | 989.0 | 37.2 | 15.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 38.7 | 1.00× |
| 2× | 52.4 | 1.35× |
| 4× | 57.9 | 1.50× |