← Back to community benchmarks
Qwen3.6-35B-A3B-oQ4
Performance
16k
tokens
2,684
PP tok/s
44.4
TG tok/s
6104
TTFT (ms)
22.9
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
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 | 1,358 | 110.4 | 20.6 GB | view |
| 4k | 1,703 | 106.3 | 21.4 GB | view |
| 8k | 1,700 | 96.7 | 21.8 GB | view |
| 16k | 2,684 | 44.4 | 22.9 GB | current |
| 32k | 3,172 | 43.5 | 23.6 GB | view |
| 64k | 2,426 | 41.8 | 25.4 GB | view |
| 128k | 1,755 | 39.5 | 28.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 110.4 | 1.00× |
| 2× | 176.8 | 1.60× |
| 4× | 240.9 | 2.18× |