← Back to community benchmarks
gemma-4-E2B-it-oQ8
Performance
16k
tokens
1,726
PP tok/s
27.7
TG tok/s
9491
TTFT (ms)
6.2
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
24 GB
GPU Cores
10
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 | 1,846 | 32.0 | 6.0 GB | view |
| 4k | 1,932 | 31.0 | 6.1 GB | view |
| 8k | 1,871 | 28.2 | 6.1 GB | view |
| 16k | 1,726 | 27.7 | 6.2 GB | current |
| 32k | 1,440 | 24.7 | 6.5 GB | view |
| 64k | 905.3 | 4.7 | 7.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.0 | 1.00× |
| 2× | 14.9 | 0.47× |
| 4× | 32.1 | 1.00× |
| 8× | 59.4 | 1.86× |