← Back to community benchmarks
Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
Performance
4k
tokens
1,700
PP tok/s
59.9
TG tok/s
2410
TTFT (ms)
35.5
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.11
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,109 | 63.4 | 35.4 GB | view |
| 4k | 1,700 | 59.9 | 35.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 63.4 | 1.00× |
| 2× | 99.4 | 1.57× |
| 4× | 134.5 | 2.12× |