← Back to community benchmarks
Qwen3.6-27B-oQ6-fp16-mtp
Performance
1k
tokens
262.7
PP tok/s
26.7
TG tok/s
3899
TTFT (ms)
22.8
Peak mem (GB)
Hardware
Chip
M1 Ultra (64c)
Memory
128 GB
GPU Cores
64
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 262.7 | 26.7 | 22.8 GB | current |
| 4k | 282.8 | 26.3 | 24.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 26.7 | 1.00× |
| 2× | 33.8 | 1.27× |
| 4× | 39.6 | 1.48× |