← Back to community benchmarks
Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-qx86-hi
Performance
16k
tokens
558.6
PP tok/s
48.1
TG tok/s
29331
TTFT (ms)
34.1
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
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 583.8 | 64.9 | 33.3 GB | view |
| 4k | 639.7 | 62.0 | 33.5 GB | view |
| 8k | 587.5 | 55.8 | 33.7 GB | view |
| 16k | 558.6 | 48.1 | 34.1 GB | current |
| 32k | 503.7 | 35.2 | 34.9 GB | view |
| 64k | 419.8 | 22.2 | 36.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 64.9 | 1.00× |
| 2× | 99.2 | 1.53× |
| 4× | 112.1 | 1.73× |
| 8× | 138.8 | 2.14× |