← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
8k
tokens
600.1
PP tok/s
49.6
TG tok/s
13650
TTFT (ms)
36.7
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 501.3 | 54.1 | 35.4 GB | view |
| 4k | 600.7 | 51.8 | 36.2 GB | view |
| 8k | 600.1 | 49.6 | 36.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.1 | 1.00× |
| 2× | 81.8 | 1.51× |