← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
16k
tokens
2,149
PP tok/s
83.4
TG tok/s
7623
TTFT (ms)
21.0
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,519 | 103.3 | 19.3 GB | view |
| 4k | 2,169 | 99.2 | 20.0 GB | view |
| 8k | 2,268 | 92.3 | 20.4 GB | view |
| 16k | 2,149 | 83.4 | 21.0 GB | current |
| 32k | 1,808 | 62.8 | 22.3 GB | view |
| 64k | 1,297 | 44.3 | 25.0 GB | view |
| 128k | 805.8 | 28.1 | 30.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 103.3 | 1.00× |
| 2× | 155.7 | 1.51× |
| 4× | 197.8 | 1.91× |