← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
1,711
PP tok/s
61.8
TG tok/s
2393
TTFT (ms)
36.3
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.9
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,399 | 63.9 | 36.2 GB | view |
| 4k | 1,711 | 61.8 | 36.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 63.9 | 1.00× |
| 2× | 101.0 | 1.58× |
| 4× | 138.6 | 2.17× |