← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
8k
tokens
1,389
PP tok/s
78.4
TG tok/s
5899
TTFT (ms)
15.0
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,028 | 105.2 | 14.2 GB | view |
| 4k | 1,361 | 92.4 | 14.8 GB | view |
| 8k | 1,389 | 78.4 | 15.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 105.2 | 1.00× |
| 2× | 153.2 | 1.46× |
| 4× | 200.2 | 1.90× |