← Back to community benchmarks
Huihui-gemma-4-E4B-it-abliterated-4bit
Performance
4k
tokens
638.3
PP tok/s
21.2
TG tok/s
6417
TTFT (ms)
7.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 628.7 | 21.8 | 6.9 GB | view |
| 4k | 638.3 | 21.2 | 7.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.8 | 1.00× |
| 2× | 42.8 | 1.96× |
| 4× | 66.9 | 3.07× |