← Back to community benchmarks
Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
Performance
4k
tokens
1,379
PP tok/s
46.8
TG tok/s
2970
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,342 | 50.3 | 35.4 GB | view |
| 4k | 1,379 | 46.8 | 36.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 50.3 | 1.00× |
| 2× | 76.5 | 1.52× |
| 4× | 103.3 | 2.05× |
| 8× | 130.8 | 2.60× |