← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
8k
tokens
1,371
PP tok/s
51.1
TG tok/s
5973
TTFT (ms)
27.6
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.2
macOS
macOS 15.7.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,399 | 56.5 | 26.8 GB | view |
| 4k | 1,398 | 54.5 | 27.4 GB | view |
| 8k | 1,371 | 51.1 | 27.6 GB | current |
| 16k | 1,313 | 46.6 | 28.0 GB | view |
| 32k | 1,187 | 38.7 | 28.7 GB | view |
| 64k | 973.5 | 25.5 | 30.4 GB | view |
| 128k | 697.2 | 0.6 | 34.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 56.5 | 1.00× |
| 2× | 82.9 | 1.47× |
| 4× | 124.3 | 2.20× |