← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
64k
tokens
1,337
PP tok/s
44.6
TG tok/s
49022
TTFT (ms)
71.3
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
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,432 | 73.1 | 65.6 GB | view |
| 4k | 2,098 | 71.6 | 66.4 GB | view |
| 32k | 1,757 | 55.2 | 68.7 GB | view |
| 64k | 1,337 | 44.6 | 71.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 73.1 | 1.00× |
| 2× | 68.2 | 0.93× |
| 4× | 141.1 | 1.93× |