← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
1k
tokens
2,360
PP tok/s
74.8
TG tok/s
434
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,360 | 74.8 | 36.2 GB | current |
| 4k | 2,638 | 72.2 | 36.3 GB | view |
| 32k | 2,083 | 55.7 | 37.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 74.8 | 1.00× |
| 2× | 128.0 | 1.71× |
| 4× | 214.0 | 2.86× |
| 8× | 331.9 | 4.44× |