← Back to community benchmarks
gemma-4-E4B-it-hereticmxfp8
Performance
1k
tokens
533.8
PP tok/s
19.5
TG tok/s
1919
TTFT (ms)
7.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 533.8 | 19.5 | 7.8 GB | current |
| 4k | 605.2 | 19.0 | 7.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.5 | 1.00× |
| 2× | 38.6 | 1.98× |
| 4× | 75.8 | 3.89× |