← Back to community benchmarks
Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-oQ4
Performance
1k
tokens
725.2
PP tok/s
33.1
TG tok/s
1412
TTFT (ms)
16.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.4
macOS
macOS 26.5.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 725.2 | 33.1 | 16.5 GB | current |
| 4k | 867.4 | 32.0 | 17.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 33.1 | 1.00× |
| 2× | 49.9 | 1.51× |
| 4× | 60.3 | 1.82× |