← Back to community benchmarks
Qwen3.6-27B-MXFP4-MTP
Performance
4k
tokens
139.6
PP tok/s
10.3
TG tok/s
29334
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M1 Ultra (48c)
Memory
64 GB
GPU Cores
48
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 135.2 | 10.7 | 15.3 GB | view |
| 4k | 139.6 | 10.3 | 16.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 10.7 | 1.00× |
| 2× | 27.6 | 2.58× |
| 4× | 31.1 | 2.91× |