← Back to community benchmarks
gemma-4-e4b-it-mxfp8
Performance
4k
tokens
2,476
PP tok/s
71.9
TG tok/s
1654
TTFT (ms)
7.9
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.3.3
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,545 | 75.8 | 7.8 GB | view |
| 4k | 2,476 | 71.9 | 7.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 75.8 | 1.00× |
| 2× | 114.9 | 1.52× |
| 4× | 144.2 | 1.90× |
| 8× | 173.6 | 2.29× |