← Back to community benchmarks
gemma-4-e4b-it
Performance
16k
tokens
917.0
PP tok/s
43.0
TG tok/s
17868
TTFT (ms)
9.5
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
32 GB
GPU Cores
30
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 935.8 | 51.8 | 9.0 GB | view |
| 4k | 946.1 | 49.6 | 9.1 GB | view |
| 8k | 939.0 | 47.2 | 9.2 GB | view |
| 16k | 917.0 | 43.0 | 9.5 GB | current |
| 32k | 870.1 | 36.7 | 10.2 GB | view |
| 64k | 790.5 | 28.5 | 11.1 GB | view |
| 128k | 666.0 | 19.4 | 13.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 51.8 | 1.00× |
| 2× | 90.0 | 1.74× |
| 4× | 122.3 | 2.36× |