← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
1,732
PP tok/s
99.2
TG tok/s
2365
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
48 GB
GPU Cores
40
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 | 1,652 | 110.8 | 20.0 GB | view |
| 4k | 1,732 | 99.2 | 20.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 110.8 | 1.00× |
| 2× | 179.0 | 1.62× |
| 4× | 262.3 | 2.37× |
| 8× | 344.9 | 3.11× |