← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
2,134
PP tok/s
85.8
TG tok/s
1919
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,045 | 87.8 | 20.1 GB | view |
| 4k | 2,134 | 85.8 | 20.2 GB | current |
| 8k | 2,069 | 85.2 | 20.4 GB | view |
| 16k | 1,921 | 77.6 | 20.8 GB | view |
| 32k | 1,675 | 68.2 | 21.6 GB | view |
| 64k | 1,290 | 50.8 | 23.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 87.8 | 1.00× |
| 2× | 162.7 | 1.85× |
| 4× | 251.1 | 2.86× |
| 8× | 374.5 | 4.27× |