← Back to community benchmarks
gemma4-26b-a4b-it
Performance
1k
tokens
970.9
PP tok/s
68.4
TG tok/s
1055
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.3.6
macOS
macOS 15.7.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 970.9 | 68.4 | 20.0 GB | current |
| 4k | 1,110 | 62.9 | 20.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 68.4 | 1.00× |
| 2× | 136.8 | 2.00× |
| 4× | 273.1 | 3.99× |