← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
4k
tokens
1,050
PP tok/s
54.2
TG tok/s
3903
TTFT (ms)
19.9
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 761.3 | 54.6 | 19.2 GB | view |
| 4k | 1,050 | 54.2 | 19.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.6 | 1.00× |
| 2× | 85.9 | 1.57× |
| 4× | 107.9 | 1.98× |