← Back to community benchmarks
Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
Performance
16k
tokens
1,832
PP tok/s
56.7
TG tok/s
8941
TTFT (ms)
36.1
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.10
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,394 | 67.4 | 35.4 GB | view |
| 4k | 1,855 | 65.1 | 35.5 GB | view |
| 8k | 1,903 | 62.6 | 35.7 GB | view |
| 16k | 1,832 | 56.7 | 36.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 67.4 | 1.00× |
| 2× | 104.2 | 1.55× |
| 4× | 141.8 | 2.10× |
| 8× | 200.4 | 2.97× |