← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
16k
tokens
1,272
PP tok/s
80.3
TG tok/s
12879
TTFT (ms)
20.8
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,204 | 96.5 | 20.0 GB | view |
| 4k | 1,392 | 95.2 | 20.2 GB | view |
| 8k | 1,378 | 92.2 | 20.4 GB | view |
| 16k | 1,272 | 80.3 | 20.8 GB | current |
| 64k | 843.5 | 40.7 | 23.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 96.5 | 1.00× |
| 2× | 171.2 | 1.77× |
| 4× | 232.2 | 2.41× |
| 8× | 293.9 | 3.05× |