← Back to community benchmarks
Qwen3.6-27B-oQ8-fp16-mtp
Performance
8k
tokens
667.0
PP tok/s
26.5
TG tok/s
12283
TTFT (ms)
31.3
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 720.9 | 29.5 | 28.8 GB | view |
| 4k | 716.4 | 29.1 | 30.3 GB | view |
| 8k | 667.0 | 26.5 | 31.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 29.5 | 1.00× |
| 2× | 32.9 | 1.12× |
| 4× | 43.4 | 1.47× |