← Back to community benchmarks
gemma-4-26B-A4B-it-heretic
Performance
4k
tokens
369.9
PP tok/s
32.2
TG tok/s
11072
TTFT (ms)
14.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 359.1 | 33.3 | 14.2 GB | view |
| 4k | 369.9 | 32.2 | 14.9 GB | current |
| 8k | 365.3 | 30.4 | 15.0 GB | view |
| 16k | 349.0 | 28.9 | 15.5 GB | view |
| 32k | 302.6 | 23.6 | 15.9 GB | view |
| 64k | 236.1 | 16.6 | 17.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 33.3 | 1.00× |
| 2× | 48.1 | 1.44× |
| 4× | 53.6 | 1.61× |