← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
979.7
PP tok/s
35.6
TG tok/s
4181
TTFT (ms)
15.4
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.1
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 948.5 | 38.8 | 15.0 GB | view |
| 4k | 979.7 | 35.6 | 15.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 38.8 | 1.00× |
| 2× | 45.1 | 1.16× |
| 4× | 61.0 | 1.57× |