← Back to community benchmarks
Qwen3.6-27B-MXFP4-MTP
Performance
4k
tokens
140.2
PP tok/s
22.7
TG tok/s
29220
TTFT (ms)
16.5
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 | 135.7 | 23.6 | 15.1 GB | view |
| 4k | 140.2 | 22.7 | 16.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 23.6 | 1.00× |
| 2× | 27.9 | 1.18× |
| 4× | 31.5 | 1.33× |