← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
741.1
PP tok/s
78.7
TG tok/s
5527
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
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 | 675.3 | 82.9 | 20.1 GB | view |
| 4k | 741.1 | 78.7 | 20.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 82.9 | 1.00× |
| 2× | 123.5 | 1.49× |
| 4× | 149.8 | 1.81× |