← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
16k
tokens
816.7
PP tok/s
62.5
TG tok/s
20061
TTFT (ms)
21.0
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 781.5 | 85.6 | 19.3 GB | view |
| 4k | 895.4 | 80.9 | 20.0 GB | view |
| 8k | 878.8 | 75.9 | 20.4 GB | view |
| 16k | 816.7 | 62.5 | 21.0 GB | current |
| 32k | 699.1 | 48.1 | 22.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 85.6 | 1.00× |
| 2× | 130.5 | 1.52× |
| 4× | 260.1 | 3.04× |