← Back to community benchmarks
gemma-4-e4b-it
Performance
128k
tokens
511.3
PP tok/s
13.6
TG tok/s
256347
TTFT (ms)
12.3
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
131,072
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 906.9 | 46.9 | 9.0 GB | view |
| 4k | 779.1 | 45.1 | 9.1 GB | view |
| 8k | 768.5 | 41.7 | 9.2 GB | view |
| 16k | 748.0 | 36.8 | 9.5 GB | view |
| 32k | 692.6 | 30.4 | 9.9 GB | view |
| 64k | 617.9 | 20.9 | 10.5 GB | view |
| 128k | 511.3 | 13.6 | 12.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 46.9 | 1.00× |
| 2× | 64.2 | 1.37× |
| 4× | 75.9 | 1.62× |