← Back to community benchmarks
Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-oQ3-mtp
Performance
4k
tokens
735.5
PP tok/s
78.6
TG tok/s
5569
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
32 GB
GPU Cores
38
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 607.4 | 82.8 | 15.9 GB | view |
| 4k | 735.5 | 78.6 | 16.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 82.8 | 1.00× |
| 2× | 113.7 | 1.37× |
| 4× | 325.3 | 3.93× |