← Back to community benchmarks
Qwen3.5-27B-Uncensored-HauhauCS-Aggressive
Performance
8k
tokens
100.2
PP tok/s
15.5
TG tok/s
81788
TTFT (ms)
17.1
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.3.4
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 99.9 | 16.5 | 15.1 GB | view |
| 4k | 101.2 | 16.0 | 16.5 GB | view |
| 8k | 100.2 | 15.5 | 17.1 GB | current |
| 16k | 97.4 | 14.6 | 18.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 16.5 | 1.00× |
| 2× | 28.4 | 1.72× |
| 4× | 30.0 | 1.82× |