← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
16k
tokens
184.0
PP tok/s
19.6
TG tok/s
89026
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev2
macOS
macOS 15.7.5
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 188.1 | 26.8 | 16.7 GB | view |
| 4k | 200.1 | 27.3 | 18.2 GB | view |
| 8k | 202.5 | 26.1 | 19.2 GB | view |
| 16k | 184.0 | 19.6 | 20.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 26.8 | 1.00× |
| 2× | 23.1 | 0.86× |
| 4× | 77.8 | 2.90× |
| 8× | 91.8 | 3.43× |