← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
1,361
PP tok/s
48.7
TG tok/s
3010
TTFT (ms)
48.3
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.4
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,115 | 51.0 | 47.7 GB | view |
| 4k | 1,361 | 48.7 | 48.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 51.0 | 1.00× |
| 2× | 48.4 | 0.95× |
| 4× | 84.6 | 1.66× |
| 8× | 78.9 | 1.55× |