← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
669.8
PP tok/s
65.8
TG tok/s
1529
TTFT (ms)
27.7
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 669.8 | 65.8 | 27.7 GB | current |
| 4k | 682.7 | 56.9 | 28.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 65.8 | 1.00× |
| 2× | 92.2 | 1.40× |
| 4× | 111.6 | 1.70× |