← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
32k
tokens
1,179
PP tok/s
47.5
TG tok/s
27805
TTFT (ms)
16.5
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
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,400 | 70.5 | 14.6 GB | view |
| 4k | 1,327 | 66.9 | 15.1 GB | view |
| 8k | 1,362 | 61.4 | 15.3 GB | view |
| 16k | 1,301 | 55.5 | 15.7 GB | view |
| 32k | 1,179 | 47.5 | 16.5 GB | current |
| 64k | 980.4 | 29.2 | 18.2 GB | view |
| 128k | 694.2 | 0.6 | 22.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 70.5 | 1.00× |
| 2× | 103.4 | 1.47× |
| 4× | 154.0 | 2.18× |