← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
414.5
PP tok/s
52.9
TG tok/s
2470
TTFT (ms)
14.2
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
32 GB
GPU Cores
32
Software
oMLX
v0.3.5
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 414.5 | 52.9 | 14.2 GB | current |
| 4k | 416.9 | 45.5 | 14.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 52.9 | 1.00× |
| 2× | 61.0 | 1.15× |
| 4× | 66.2 | 1.25× |