← Back to community benchmarks
Qwen3.6-35B-A3B-oQ4-mtp
Performance
8k
tokens
1,709
PP tok/s
100.6
TG tok/s
4794
TTFT (ms)
21.2
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,369 | 109.6 | 19.9 GB | view |
| 4k | 1,708 | 103.6 | 20.7 GB | view |
| 8k | 1,709 | 100.6 | 21.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 109.6 | 1.00× |
| 2× | 175.8 | 1.60× |
| 4× | 239.2 | 2.18× |
| 8× | 300.8 | 2.74× |