← Back to community benchmarks
Qwen3.6-27B-MXFP4-MTP
Performance
1k
tokens
241.4
PP tok/s
31.5
TG tok/s
4243
TTFT (ms)
15.1
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.4
macOS
macOS 26.5.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 241.4 | 31.5 | 15.1 GB | current |
| 4k | 248.5 | 30.5 | 16.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 31.5 | 1.00× |
| 2× | 56.3 | 1.79× |
| 4× | 64.7 | 2.05× |