← Back to community benchmarks
Qwen3.6-35B-A3B-oQ4-fp16-mtp
Performance
32k
tokens
1,142
PP tok/s
70.3
TG tok/s
28683
TTFT (ms)
23.9
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
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,194 | 94.1 | 20.4 GB | view |
| 4k | 1,540 | 87.0 | 21.2 GB | view |
| 8k | 1,548 | 84.3 | 21.5 GB | view |
| 16k | 1,435 | 78.8 | 22.4 GB | view |
| 32k | 1,142 | 70.3 | 23.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 94.1 | 1.00× |
| 2× | 141.3 | 1.50× |
| 4× | 188.6 | 2.00× |
| 8× | 229.6 | 2.44× |