← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
368.7
PP tok/s
33.0
TG tok/s
2777
TTFT (ms)
14.2
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 368.7 | 33.0 | 14.2 GB | current |
| 4k | 369.6 | 31.0 | 14.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 33.0 | 1.00× |
| 2× | 48.0 | 1.45× |
| 4× | 55.8 | 1.69× |