← Back to community benchmarks
gemma-4-E4B-it-oQ8
Performance
16k
tokens
1,178
PP tok/s
35.8
TG tok/s
13911
TTFT (ms)
8.4
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 980.8 | 41.6 | 8.0 GB | view |
| 4k | 1,181 | 40.3 | 8.1 GB | view |
| 8k | 1,203 | 38.4 | 8.2 GB | view |
| 16k | 1,178 | 35.8 | 8.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 41.6 | 1.00× |
| 2× | 79.5 | 1.91× |
| 4× | 114.9 | 2.76× |
| 8× | 124.6 | 3.00× |