← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
8k
tokens
3,911
PP tok/s
115.3
TG tok/s
2095
TTFT (ms)
20.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,320 | 134.3 | 19.3 GB | view |
| 4k | 3,850 | 131.0 | 20.0 GB | view |
| 8k | 3,911 | 115.3 | 20.5 GB | current |
| 16k | 3,774 | 116.7 | 21.2 GB | view |
| 32k | 3,365 | 107.7 | 22.7 GB | view |
| 64k | 2,447 | 87.6 | 25.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 134.3 | 1.00× |
| 2× | 205.0 | 1.53× |
| 4× | 329.0 | 2.45× |