← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
32k
tokens
1,085
PP tok/s
60.2
TG tok/s
30194
TTFT (ms)
21.6
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.2.6
macOS
macOS 15.6.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,329 | 100.0 | 20.1 GB | view |
| 4k | 1,395 | 100.3 | 20.2 GB | view |
| 8k | 1,347 | 92.3 | 20.4 GB | view |
| 16k | 1,246 | 79.5 | 20.8 GB | view |
| 32k | 1,085 | 60.2 | 21.6 GB | current |
| 64k | 842.1 | 41.5 | 23.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 100.0 | 1.00× |
| 2× | 168.4 | 1.68× |
| 4× | 225.5 | 2.25× |
| 8× | 285.2 | 2.85× |