← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
4k
tokens
443.6
PP tok/s
57.0
TG tok/s
9233
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.3.7
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 357.2 | 61.7 | 19.3 GB | view |
| 4k | 443.6 | 57.0 | 20.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 61.7 | 1.00× |
| 2× | 79.5 | 1.29× |
| 4× | 85.8 | 1.39× |