← Back to community benchmarks
Huihui-Qwen3.5-9B-abliterated
Performance
1k
tokens
185.8
PP tok/s
20.4
TG tok/s
5512
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.7
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 185.8 | 20.4 | 5.7 GB | current |
| 4k | 184.0 | 19.1 | 6.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.4 | 1.00× |
| 2× | 39.7 | 1.95× |
| 4× | 39.9 | 1.96× |