← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
543.4
PP tok/s
49.7
TG tok/s
1884
TTFT (ms)
14.3
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 543.4 | 49.7 | 14.3 GB | current |
| 4k | 597.9 | 46.4 | 14.9 GB | view |
| 8k | 597.7 | 43.9 | 15.1 GB | view |
| 16k | 551.7 | 38.7 | 15.6 GB | view |
| 32k | 475.2 | 32.3 | 16.5 GB | view |
| 64k | 372.7 | 26.7 | 18.5 GB | view |
| 128k | 241.0 | 18.5 | 22.7 GB | view |
| 195k | 174.0 | 11.5 | 27.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.7 | 1.00× |
| 2× | 51.6 | 1.04× |
| 4× | 68.0 | 1.37× |
| 8× | 78.6 | 1.58× |