← Back to community benchmarks
Qwen3.6-27B-MXFP4-CRACK-MTP
Performance
4k
tokens
117.4
PP tok/s
18.2
TG tok/s
34903
TTFT (ms)
19.5
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.10
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 119.6 | 19.3 | 16.7 GB | view |
| 4k | 117.4 | 18.2 | 19.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.3 | 1.00× |
| 2× | 21.7 | 1.12× |
| 4× | 43.5 | 2.25× |