← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
453.1
PP tok/s
54.3
TG tok/s
2260
TTFT (ms)
13.3
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.4
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 453.1 | 54.3 | 13.3 GB | current |
| 4k | 448.1 | 47.2 | 13.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.3 | 1.00× |
| 2× | 66.2 | 1.22× |
| 4× | 74.5 | 1.37× |