← Back to community benchmarks
gemma-4-26B-A4B-it-heretic
Performance
1k
tokens
298.1
PP tok/s
27.9
TG tok/s
3435
TTFT (ms)
14.2
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 298.1 | 27.9 | 14.2 GB | current |
| 4k | 287.2 | 27.6 | 14.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 27.9 | 1.00× |
| 2× | 39.5 | 1.42× |
| 4× | 47.1 | 1.69× |