← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
8k
tokens
3,281
PP tok/s
101.8
TG tok/s
2497
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M5 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,967 | 112.8 | 19.3 GB | view |
| 4k | 3,106 | 109.0 | 20.0 GB | view |
| 8k | 3,281 | 101.8 | 20.4 GB | current |
| 16k | 2,993 | 92.7 | 21.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 112.8 | 1.00× |
| 2× | 180.5 | 1.60× |
| 4× | 263.0 | 2.33× |
| 8× | 329.3 | 2.92× |