← Back to community benchmarks
Qwen3.6-35B-A3B-oQ4
Performance
16k
tokens
2,061
PP tok/s
67.9
TG tok/s
7951
TTFT (ms)
21.7
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 | 1,307 | 84.9 | 19.9 GB | view |
| 4k | 2,080 | 81.3 | 20.7 GB | view |
| 8k | 2,194 | 75.2 | 21.1 GB | view |
| 16k | 2,061 | 67.9 | 21.7 GB | current |
| 32k | 1,745 | 55.2 | 23.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 84.9 | 1.00× |
| 2× | 130.2 | 1.53× |
| 4× | 179.7 | 2.12× |