← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
16k
tokens
484.5
PP tok/s
45.6
TG tok/s
33819
TTFT (ms)
36.6
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.5.1
macOS
macOS 27.0
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 496.6 | 48.5 | 35.4 GB | view |
| 4k | 600.9 | 40.3 | 36.1 GB | view |
| 8k | 536.0 | 44.8 | 36.3 GB | view |
| 16k | 484.5 | 45.6 | 36.6 GB | current |
| 32k | 397.4 | 42.2 | 37.2 GB | view |
| 64k | 298.2 | 35.3 | 37.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.5 | 1.00× |
| 2× | 78.1 | 1.61× |
| 4× | 83.8 | 1.73× |