← Back to community benchmarks
Huihui-gemma-4-26B-A4B-it-abliterated
Performance
16k
tokens
678.6
PP tok/s
39.3
TG tok/s
24145
TTFT (ms)
15.2
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 | 686.8 | 66.1 | 14.2 GB | view |
| 4k | 738.4 | 63.0 | 14.7 GB | view |
| 8k | 736.7 | 16.4 | 14.8 GB | view |
| 16k | 678.6 | 39.3 | 15.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 66.1 | 1.00× |
| 2× | 96.5 | 1.46× |
| 4× | 116.2 | 1.76× |