← Back to community benchmarks
Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
Performance
4k
tokens
893.9
PP tok/s
76.8
TG tok/s
4582
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 748.5 | 80.1 | 19.3 GB | view |
| 4k | 893.9 | 76.8 | 20.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 80.1 | 1.00× |
| 2× | 126.3 | 1.58× |
| 4× | 157.2 | 1.96× |