← Back to community benchmarks
Qwen3.6-35B-A3B-oQ6
Performance
16k
tokens
466.3
PP tok/s
43.0
TG tok/s
35140
TTFT (ms)
29.5
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
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 | 458.6 | 52.3 | 27.7 GB | view |
| 4k | 493.9 | 49.5 | 28.5 GB | view |
| 8k | 495.6 | 47.5 | 28.9 GB | view |
| 16k | 466.3 | 43.0 | 29.5 GB | current |
| 32k | 397.2 | 30.7 | 30.8 GB | view |
| 64k | 325.3 | 21.3 | 33.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 52.3 | 1.00× |
| 2× | 76.5 | 1.46× |
| 4× | 91.1 | 1.74× |
| 8× | 106.0 | 2.03× |