← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
335.5
PP tok/s
44.7
TG tok/s
3053
TTFT (ms)
13.5
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.3.4
macOS
macOS 15.7.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 335.5 | 44.7 | 13.5 GB | current |
| 32k | 347.1 | 19.5 | 15.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 44.7 | 1.00× |
| 2× | 57.6 | 1.29× |
| 8× | 75.9 | 1.70× |