← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
8k
tokens
1,165
PP tok/s
74.6
TG tok/s
7032
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M2 Ultra (60c)
Memory
64 GB
GPU Cores
60
Software
oMLX
v0.3.5
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 901.7 | 83.4 | 19.3 GB | view |
| 4k | 1,148 | 81.4 | 20.0 GB | view |
| 8k | 1,165 | 74.6 | 20.4 GB | current |
| 16k | 1,126 | 67.3 | 21.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 83.4 | 1.00× |
| 2× | 122.6 | 1.47× |
| 4× | 194.2 | 2.33× |