← Back to community benchmarks
Qwen3.6-35B-A3B-YOYO-V2-oQ8e-mtp
Performance
1k
tokens
3,130
PP tok/s
92.6
TG tok/s
327
TTFT (ms)
35.4
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.5.1
macOS
macOS 26.5.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 3,130 | 92.6 | 35.4 GB | current |
| 4k | 3,898 | 90.2 | 36.1 GB | view |
| 64k | 2,219 | 65.1 | 41.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 92.6 | 1.00× |
| 2× | 135.7 | 1.47× |
| 4× | 214.5 | 2.32× |