← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
4k
tokens
175.7
PP tok/s
29.3
TG tok/s
23317
TTFT (ms)
18.8
Peak mem (GB)
Hardware
Chip
M2 Ultra (60c)
Memory
64 GB
GPU Cores
60
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 172.0 | 22.3 | 17.3 GB | view |
| 4k | 175.7 | 29.3 | 18.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.3 | 1.00× |
| 2× | 60.9 | 2.73× |
| 4× | 122.9 | 5.51× |