← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
933.0
PP tok/s
82.0
TG tok/s
1098
TTFT (ms)
14.2
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.3.4
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 933.0 | 82.0 | 14.2 GB | current |
| 4k | 1,065 | 75.7 | 14.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 82.0 | 1.00× |
| 2× | 126.5 | 1.54× |
| 4× | 158.8 | 1.94× |