← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
1,115
PP tok/s
51.0
TG tok/s
918
TTFT (ms)
47.7
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.4
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,115 | 51.0 | 47.7 GB | current |
| 4k | 1,361 | 48.7 | 48.3 GB | view |
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× |