← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
32k
tokens
338.3
PP tok/s
30.9
TG tok/s
96871
TTFT (ms)
16.5
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
64 GB
GPU Cores
24
Software
oMLX
v0.3.8
macOS
macOS 26.3.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 348.1 | 48.3 | 14.3 GB | view |
| 4k | 371.0 | 45.9 | 14.9 GB | view |
| 8k | 373.6 | 43.4 | 15.1 GB | view |
| 16k | 364.8 | 39.1 | 15.6 GB | view |
| 32k | 338.3 | 30.9 | 16.5 GB | current |
| 64k | 296.0 | 19.9 | 17.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.3 | 1.00× |
| 2× | 61.3 | 1.27× |
| 4× | 71.2 | 1.47× |
| 8× | 79.2 | 1.64× |