← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
64k
tokens
254.2
PP tok/s
23.5
TG tok/s
257849
TTFT (ms)
39.7
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.4.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 298.4 | 33.3 | 28.8 GB | view |
| 4k | 317.5 | 32.2 | 30.3 GB | view |
| 64k | 254.2 | 23.5 | 39.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 33.3 | 1.00× |
| 2× | 39.8 | 1.20× |
| 4× | 18.8 | 0.56× |