← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
1,975
PP tok/s
62.1
TG tok/s
2074
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 | 1,762 | 65.8 | 36.2 GB | view |
| 4k | 1,975 | 62.1 | 36.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 65.8 | 1.00× |
| 2× | 102.4 | 1.56× |
| 4× | 142.6 | 2.17× |
| 8× | 207.3 | 3.15× |