← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
1k
tokens
1,527
PP tok/s
94.7
TG tok/s
671
TTFT (ms)
20.1
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.18
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,527 | 94.7 | 20.1 GB | current |
| 4k | 2,221 | 90.5 | 21.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 94.7 | 1.00× |
| 2× | 149.5 | 1.58× |
| 4× | 201.6 | 2.13× |
| 8× | 244.4 | 2.58× |