← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
2,256
PP tok/s
62.0
TG tok/s
1816
TTFT (ms)
37.1
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.19
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,826 | 64.2 | 36.2 GB | view |
| 4k | 2,256 | 62.0 | 37.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 64.2 | 1.00× |
| 2× | 99.8 | 1.55× |
| 4× | 138.8 | 2.16× |