← Back to community benchmarks
Qwen3.6-35B-A3B-oQ4-mtp
Performance
4k
tokens
457.8
PP tok/s
48.3
TG tok/s
8948
TTFT (ms)
21.2
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 384.0 | 52.7 | 20.4 GB | view |
| 4k | 457.8 | 48.3 | 21.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 52.7 | 1.00× |
| 2× | 75.8 | 1.44× |
| 4× | 90.8 | 1.72× |