← Back to community benchmarks
Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
Performance
1k
tokens
1,166
PP tok/s
59.5
TG tok/s
878
TTFT (ms)
35.4
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.21
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,166 | 59.5 | 35.4 GB | current |
| 4k | 1,899 | 54.8 | 36.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 59.5 | 1.00× |
| 2× | 97.1 | 1.63× |
| 4× | 129.8 | 2.18× |
| 8× | 177.0 | 2.97× |