← Back to community benchmarks
Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
Performance
8k
tokens
1,060
PP tok/s
67.9
TG tok/s
7730
TTFT (ms)
20.5
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 899.1 | 66.4 | 19.3 GB | view |
| 4k | 1,236 | 61.9 | 20.0 GB | view |
| 8k | 1,060 | 67.9 | 20.5 GB | current |
| 16k | 995.2 | 61.4 | 21.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 66.4 | 1.00× |
| 2× | 123.3 | 1.86× |
| 4× | 180.5 | 2.72× |
| 8× | 211.5 | 3.19× |