← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
8k
tokens
1,677
PP tok/s
93.7
TG tok/s
4886
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.2.10
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,732 | 114.4 | 20.1 GB | view |
| 4k | 1,755 | 108.5 | 20.2 GB | view |
| 8k | 1,677 | 93.7 | 20.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 114.4 | 1.00× |
| 2× | 174.5 | 1.53× |
| 4× | 272.5 | 2.38× |
| 8× | 346.5 | 3.03× |