← Back to community benchmarks
gemma-4-e4b-it-mxfp8
Performance
4k
tokens
611.5
PP tok/s
19.2
TG tok/s
6699
TTFT (ms)
7.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 544.9 | 20.2 | 7.7 GB | view |
| 4k | 611.5 | 19.2 | 7.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.2 | 1.00× |
| 2× | 36.0 | 1.78× |
| 4× | 38.2 | 1.89× |