← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
723.2
PP tok/s
59.5
TG tok/s
5664
TTFT (ms)
19.4
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.4
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 655.7 | 63.1 | 18.9 GB | view |
| 4k | 723.2 | 59.5 | 19.4 GB | current |
| 16k | 519.2 | 20.3 | 20.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 63.1 | 1.00× |
| 2× | 91.8 | 1.45× |
| 4× | 103.1 | 1.63× |