← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
510.1
PP tok/s
56.9
TG tok/s
8029
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 559.6 | 59.3 | 20.1 GB | view |
| 4k | 510.1 | 56.9 | 20.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 59.3 | 1.00× |
| 2× | 84.2 | 1.42× |
| 4× | 74.7 | 1.26× |