← Back to community benchmarks
qwen3.5-9b-uncensored-hauhaucs-aggressiveoq8
Performance
1k
tokens
404.4
PP tok/s
27.6
TG tok/s
2532
TTFT (ms)
9.9
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 404.4 | 27.6 | 9.9 GB | current |
| 4k | 409.8 | 27.0 | 10.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 27.6 | 1.00× |
| 2× | 52.0 | 1.88× |
| 4× | 58.2 | 2.11× |