← Back to community benchmarks
Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
Performance
4k
tokens
437.4
PP tok/s
41.7
TG tok/s
9365
TTFT (ms)
19.4
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 15.7.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 404.7 | 44.1 | 19.2 GB | view |
| 4k | 437.4 | 41.7 | 19.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 44.1 | 1.00× |
| 2× | 67.4 | 1.53× |
| 4× | 81.9 | 1.86× |