← Back to community benchmarks
gemma-4-e4b-it-mxfp8
Performance
16k
tokens
2,174
PP tok/s
56.1
TG tok/s
7537
TTFT (ms)
8.2
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.4
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,541 | 70.6 | 7.8 GB | view |
| 4k | 2,100 | 67.5 | 7.9 GB | view |
| 8k | 2,191 | 62.3 | 8.0 GB | view |
| 16k | 2,174 | 56.1 | 8.2 GB | current |
| 32k | 1,893 | 47.2 | 8.7 GB | view |
| 64k | 1,676 | 36.0 | 9.3 GB | view |
| 128k | 1,113 | 17.6 | 11.1 GB | view |
| 195k | 929.3 | 13.1 | 12.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 70.6 | 1.00× |
| 2× | 113.0 | 1.60× |