← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
16k
tokens
4,101
PP tok/s
92.5
TG tok/s
3995
TTFT (ms)
37.6
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.5.3
macOS
macOS 26.5.2
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 3,479 | 95.9 | 35.5 GB | view |
| 4k | 4,593 | 99.2 | 36.4 GB | view |
| 8k | 4,478 | 93.7 | 36.8 GB | view |
| 16k | 4,101 | 92.5 | 37.6 GB | current |
| 32k | 3,361 | 86.1 | 39.0 GB | view |
| 64k | 2,330 | 71.9 | 42.0 GB | view |
| 128k | 1,395 | 59.1 | 47.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 95.9 | 1.00× |
| 2× | 170.6 | 1.78× |
| 4× | 255.3 | 2.66× |