← Back to community benchmarks
Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
Performance
4k
tokens
2,042
PP tok/s
74.8
TG tok/s
2006
TTFT (ms)
28.3
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.19
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,400 | 77.6 | 27.3 GB | view |
| 4k | 2,042 | 74.8 | 28.3 GB | current |
| 8k | 2,114 | 71.0 | 28.6 GB | view |
| 16k | 2,013 | 64.8 | 29.3 GB | view |
| 32k | 1,730 | 54.2 | 30.6 GB | view |
| 64k | 1,293 | 41.5 | 33.2 GB | view |
| 128k | 823.8 | 25.3 | 38.6 GB | view |
| 195k | 596.4 | 11.9 | 44.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 77.6 | 1.00× |
| 2× | 115.6 | 1.49× |
| 4× | 148.4 | 1.91× |
| 8× | 174.2 | 2.24× |