← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
1k
tokens
388.0
PP tok/s
21.9
TG tok/s
2639
TTFT (ms)
28.3
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.3.9rc1
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 388.0 | 21.9 | 28.3 GB | current |
| 4k | 421.8 | 21.6 | 29.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.9 | 1.00× |
| 2× | 38.6 | 1.76× |
| 4× | 57.7 | 2.63× |