← Back to community benchmarks
Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
Performance
1k
tokens
1,071
PP tok/s
76.3
TG tok/s
957
TTFT (ms)
27.3
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,071 | 76.3 | 27.3 GB | current |
| 4k | 1,339 | 71.0 | 27.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 76.3 | 1.00× |
| 2× | 123.7 | 1.62× |
| 4× | 163.1 | 2.14× |
| 8× | 204.4 | 2.68× |