← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
4k
tokens
235.9
PP tok/s
26.4
TG tok/s
17362
TTFT (ms)
30.3
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.9
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 234.8 | 25.7 | 28.8 GB | view |
| 4k | 235.9 | 26.4 | 30.3 GB | current |
| 8k | 213.9 | 23.3 | 31.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 25.7 | 1.00× |
| 2× | 30.1 | 1.17× |
| 4× | 37.6 | 1.46× |