← Back to community benchmarks
Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-qx86-hi
Performance
4k
tokens
639.8
PP tok/s
64.7
TG tok/s
6402
TTFT (ms)
33.5
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 563.0 | 68.1 | 33.3 GB | view |
| 4k | 639.8 | 64.7 | 33.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 68.1 | 1.00× |
| 2× | 87.8 | 1.29× |
| 4× | 107.9 | 1.58× |