← Back to community benchmarks
Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
Performance
4k
tokens
571.4
PP tok/s
50.2
TG tok/s
7169
TTFT (ms)
28.3
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.0
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 463.6 | 53.0 | 27.3 GB | view |
| 4k | 571.4 | 50.2 | 28.3 GB | current |
| 8k | 572.7 | 47.1 | 28.6 GB | view |
| 16k | 553.4 | 42.5 | 29.3 GB | view |
| 32k | 506.0 | 35.4 | 30.6 GB | view |
| 64k | 406.9 | 26.0 | 33.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 53.0 | 1.00× |
| 2× | 73.1 | 1.38× |
| 4× | 90.6 | 1.71× |