← Back to community benchmarks
Qwen3.5-35B-A3B5.5bit
Performance
4k
tokens
695.0
PP tok/s
71.5
TG tok/s
5893
TTFT (ms)
23.4
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.2.7
macOS
macOS 15.7.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 590.0 | 72.9 | 23.3 GB | view |
| 4k | 695.0 | 71.5 | 23.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 72.9 | 1.00× |
| 2× | 105.8 | 1.45× |
| 4× | 127.1 | 1.74× |