← Back to community benchmarks
Qwen3.5-9B-Uncensored-HauhauCS-Aggressive
Performance
4k
tokens
220.5
PP tok/s
10.9
TG tok/s
18576
TTFT (ms)
10.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 211.6 | 11.1 | 10.3 GB | view |
| 4k | 220.5 | 10.9 | 10.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 11.1 | 1.00× |
| 2× | 21.9 | 1.97× |
| 4× | 37.5 | 3.38× |