← Back to community benchmarks
Huihui-gemma-4-E4B-it-abliteratedoQ4
Performance
4k
tokens
628.1
PP tok/s
29.8
TG tok/s
6521
TTFT (ms)
4.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 571.8 | 30.5 | 4.7 GB | view |
| 4k | 628.1 | 29.8 | 4.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 30.5 | 1.00× |
| 2× | 58.4 | 1.91× |
| 4× | 113.8 | 3.73× |