← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
32k
tokens
1,754
PP tok/s
55.1
TG tok/s
18684
TTFT (ms)
68.7
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,427 | 73.4 | 65.6 GB | view |
| 4k | 2,079 | 71.7 | 66.4 GB | view |
| 32k | 1,754 | 55.1 | 68.7 GB | current |
| 64k | 1,332 | 44.2 | 71.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 73.4 | 1.00× |
| 2× | 70.1 | 0.96× |
| 4× | 136.3 | 1.86× |