← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
591.1
PP tok/s
1.8
TG tok/s
6929
TTFT (ms)
72.7
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.11
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 375.4 | 1.8 | 72.6 GB | view |
| 4k | 591.1 | 1.8 | 72.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 1.8 | 1.00× |
| 2× | 3.6 | 2.00× |
| 4× | 7.0 | 3.89× |