← Back to community benchmarks
Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
Performance
4k
tokens
674.7
PP tok/s
52.2
TG tok/s
6071
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip
M3 Pro (18c)
Memory
36 GB
GPU Cores
18
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 577.3 | 50.0 | 19.3 GB | view |
| 4k | 674.7 | 52.2 | 20.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 50.0 | 1.00× |
| 2× | 83.4 | 1.67× |
| 4× | 110.8 | 2.22× |
| 8× | 133.3 | 2.67× |