← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
612.9
PP tok/s
49.3
TG tok/s
1671
TTFT (ms)
15.3
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
64 GB
GPU Cores
16
Software
oMLX
v0.3.2
macOS
macOS 15.7.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 612.9 | 49.3 | 15.3 GB | current |
| 4k | 605.5 | 46.7 | 15.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.3 | 1.00× |
| 2× | 65.0 | 1.32× |
| 4× | 75.8 | 1.54× |