← Back to community benchmarks
Qwen3.6-27B-UD4bit
Performance
8k
tokens
196.3
PP tok/s
13.2
TG tok/s
41737
TTFT (ms)
27.3
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.3.8rc1
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 191.6 | 13.8 | 25.2 GB | view |
| 4k | 201.7 | 13.6 | 26.6 GB | view |
| 8k | 196.3 | 13.2 | 27.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 13.8 | 1.00× |
| 2× | 15.6 | 1.13× |
| 4× | 24.8 | 1.80× |