← Back to community benchmarks
gemma-4-26B-A4B-it-heretic
Performance
1k
tokens
1,244
PP tok/s
72.7
TG tok/s
823
TTFT (ms)
14.3
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,244 | 72.7 | 14.3 GB | current |
| 4k | 1,871 | 67.6 | 14.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 72.7 | 1.00× |
| 2× | 144.9 | 1.99× |
| 4× | 285.7 | 3.93× |