← Back to community benchmarks
Qwen3.6-35B-A3B-UD-Q6_K_XL
Performance
32k
tokens
3,154
PP tok/s
72.4
TG tok/s
10390
TTFT (ms)
35.9
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.2.dev2
macOS
macOS 26.6
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,666 | 84.9 | 32.8 GB | view |
| 4k | 3,880 | 85.0 | 33.5 GB | view |
| 8k | 3,712 | 74.8 | 33.9 GB | view |
| 16k | 3,654 | 81.4 | 34.5 GB | view |
| 32k | 3,154 | 72.4 | 35.9 GB | current |
| 64k | 2,324 | 64.4 | 38.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 84.9 | 1.00× |
| 2× | 106.6 | 1.26× |
| 4× | 176.9 | 2.08× |