← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
1k
tokens
1,696
PP tok/s
111.3
TG tok/s
604
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,696 | 111.3 | 20.0 GB | current |
| 4k | 1,745 | 103.3 | 20.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 111.3 | 1.00× |
| 2× | 185.0 | 1.66× |
| 4× | 272.1 | 2.44× |