← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
8k
tokens
1,534
PP tok/s
60.2
TG tok/s
5341
TTFT (ms)
26.6
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.10
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,954 | 45.1 | 25.8 GB | view |
| 4k | 1,400 | 63.2 | 26.5 GB | view |
| 8k | 1,534 | 60.2 | 26.6 GB | current |
| 16k | 1,658 | 57.4 | 27.1 GB | view |
| 32k | 2,125 | 64.8 | 28.0 GB | view |
| 64k | 1,855 | 42.8 | 30.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 45.1 | 1.00× |
| 2× | 101.2 | 2.24× |
| 4× | 127.2 | 2.82× |