← Back to community benchmarks
Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
Performance
8k
tokens
1,668
PP tok/s
89.3
TG tok/s
4912
TTFT (ms)
28.6
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,259 | 94.4 | 27.3 GB | view |
| 4k | 1,662 | 92.1 | 28.1 GB | view |
| 8k | 1,668 | 89.3 | 28.6 GB | current |
| 16k | 1,566 | 82.6 | 29.3 GB | view |
| 32k | 1,354 | 75.8 | 30.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 94.4 | 1.00× |
| 2× | 144.2 | 1.53× |
| 4× | 197.4 | 2.09× |