← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
342.1
PP tok/s
48.3
TG tok/s
2993
TTFT (ms)
14.0
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.3.4
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 342.1 | 48.3 | 14.0 GB | current |
| 4k | 371.2 | 44.5 | 14.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.3 | 1.00× |
| 2× | 96.6 | 2.00× |
| 4× | 193.4 | 4.00× |