← Back to community benchmarks
Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-abliterated-OptiQ-3.7bpw
Performance
4k
tokens
90.7
PP tok/s
17.7
TG tok/s
45137
TTFT (ms)
15.6
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
32 GB
GPU Cores
30
Software
oMLX
v0.4.4
macOS
macOS 26.5.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 89.0 | 18.2 | 14.3 GB | view |
| 4k | 90.7 | 17.7 | 15.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.2 | 1.00× |
| 2× | 20.0 | 1.10× |