← Back to community benchmarks
Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
Performance
1k
tokens
658.2
PP tok/s
78.7
TG tok/s
1556
TTFT (ms)
19.2
Peak mem (GB)
Hardware
Chip
M3 Max (30c)
Memory
36 GB
GPU Cores
30
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 658.2 | 78.7 | 19.2 GB | current |
| 4k | 786.3 | 60.2 | 19.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 78.7 | 1.00× |
| 2× | 106.4 | 1.35× |
| 4× | 162.5 | 2.06× |