← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
4k
tokens
152.2
PP tok/s
22.4
TG tok/s
26903
TTFT (ms)
18.1
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 147.5 | 23.4 | 16.7 GB | view |
| 4k | 152.2 | 22.4 | 18.1 GB | current |
| 8k | 150.9 | 21.9 | 19.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 23.4 | 1.00× |
| 2× | 27.3 | 1.17× |
| 4× | 29.9 | 1.28× |