← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
1k
tokens
188.5
PP tok/s
20.0
TG tok/s
5433
TTFT (ms)
16.4
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
64 GB
GPU Cores
38
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 | 188.5 | 20.0 | 16.4 GB | current |
| 4k | 195.0 | 19.4 | 17.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.0 | 1.00× |
| 2× | 33.4 | 1.67× |
| 4× | 38.0 | 1.90× |