← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
8k
tokens
2,098
PP tok/s
87.4
TG tok/s
3905
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,487 | 96.0 | 20.0 GB | view |
| 4k | 2,017 | 92.1 | 20.2 GB | view |
| 8k | 2,098 | 87.4 | 20.4 GB | current |
| 16k | 1,940 | 79.4 | 20.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 96.0 | 1.00× |
| 2× | 165.8 | 1.73× |
| 4× | 264.3 | 2.75× |