← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
1,067
PP tok/s
95.8
TG tok/s
3838
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,361 | 95.7 | 20.0 GB | view |
| 4k | 1,067 | 95.8 | 20.2 GB | current |
| 8k | 1,091 | 90.5 | 20.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 95.7 | 1.00× |
| 2× | 162.6 | 1.70× |