← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
4k
tokens
1,959
PP tok/s
93.2
TG tok/s
2091
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,182 | 97.2 | 19.2 GB | view |
| 4k | 1,959 | 93.2 | 20.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 97.2 | 1.00× |
| 2× | 151.9 | 1.56× |
| 4× | 198.3 | 2.04× |