← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
1,768
PP tok/s
56.4
TG tok/s
2316
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.2
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,938 | 59.0 | 15.3 GB | view |
| 4k | 1,768 | 56.4 | 15.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 59.0 | 1.00× |
| 2× | 80.0 | 1.36× |
| 4× | 111.7 | 1.89× |