← Back to community benchmarks
gemma-4-e4b-it
Performance
32k
tokens
1,666
PP tok/s
58.1
TG tok/s
19664
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.5
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,335 | 106.2 | 5.6 GB | view |
| 4k | 2,387 | 99.1 | 5.7 GB | view |
| 8k | 2,262 | 95.0 | 5.8 GB | view |
| 16k | 2,000 | 79.8 | 6.0 GB | view |
| 32k | 1,666 | 58.1 | 6.7 GB | current |
| 64k | 1,227 | 41.0 | 7.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 106.2 | 1.00× |
| 2× | 134.3 | 1.26× |