← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
8k
tokens
198.5
PP tok/s
30.1
TG tok/s
41274
TTFT (ms)
19.2
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 193.0 | 32.8 | 16.8 GB | view |
| 4k | 200.4 | 31.3 | 18.2 GB | view |
| 8k | 198.5 | 30.1 | 19.2 GB | current |
| 16k | 192.7 | 27.6 | 20.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.8 | 1.00× |
| 2× | 39.7 | 1.21× |
| 4× | 45.6 | 1.39× |