← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
1k
tokens
824.6
PP tok/s
86.7
TG tok/s
1242
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 824.6 | 86.7 | 20.0 GB | current |
| 4k | 900.5 | 83.1 | 20.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 86.7 | 1.00× |
| 2× | 136.1 | 1.57× |
| 4× | 170.1 | 1.96× |