← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
8k
tokens
2,168
PP tok/s
64.8
TG tok/s
3779
TTFT (ms)
66.8
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,450 | 71.6 | 65.7 GB | view |
| 4k | 2,108 | 70.0 | 66.4 GB | view |
| 8k | 2,168 | 64.8 | 66.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 71.6 | 1.00× |
| 2× | 67.0 | 0.94× |
| 4× | 116.5 | 1.63× |