← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
1k
tokens
304.8
PP tok/s
45.0
TG tok/s
3360
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 304.8 | 45.0 | 16.7 GB | current |
| 4k | 321.9 | 43.5 | 18.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 45.0 | 1.00× |
| 2× | 57.1 | 1.27× |
| 4× | 64.7 | 1.44× |