← Back to community benchmarks
Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
Performance
4k
tokens
2,330
PP tok/s
74.8
TG tok/s
1758
TTFT (ms)
35.5
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.10
macOS
macOS 15.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,677 | 77.9 | 35.3 GB | view |
| 4k | 2,330 | 74.8 | 35.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 77.9 | 1.00× |
| 2× | 144.6 | 1.86× |
| 4× | 234.8 | 3.01× |