← Back to community benchmarks
gemma-4-e4b-it-mxfp8
Performance
1k
tokens
504.9
PP tok/s
16.3
TG tok/s
2028
TTFT (ms)
8.6
Peak mem (GB)
Hardware
Chip
M3 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.7
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 504.9 | 16.3 | 8.6 GB | current |
| 4k | 519.4 | 16.1 | 8.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 16.3 | 1.00× |
| 2× | 27.3 | 1.67× |
| 4× | 30.6 | 1.88× |