← Back to community benchmarks
Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-oQ3-mtp
Performance
4k
tokens
433.3
PP tok/s
53.9
TG tok/s
9452
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
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 | 369.2 | 56.5 | 15.9 GB | view |
| 4k | 433.3 | 53.9 | 16.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 56.5 | 1.00× |
| 2× | 74.4 | 1.32× |
| 4× | 88.4 | 1.56× |