← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
724.8
PP tok/s
76.5
TG tok/s
5651
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 683.7 | 78.9 | 20.1 GB | view |
| 4k | 724.8 | 76.5 | 20.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 78.9 | 1.00× |
| 2× | 119.4 | 1.51× |
| 4× | 142.9 | 1.81× |