← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
16k
tokens
2,127
PP tok/s
81.1
TG tok/s
7702
TTFT (ms)
21.0
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,512 | 101.1 | 19.3 GB | view |
| 4k | 2,204 | 96.9 | 20.0 GB | view |
| 8k | 2,266 | 90.6 | 20.4 GB | view |
| 16k | 2,127 | 81.1 | 21.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 101.1 | 1.00× |
| 2× | 201.8 | 2.00× |
| 4× | 403.7 | 3.99× |
| 8× | 803.6 | 7.95× |