← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
1,710
PP tok/s
78.5
TG tok/s
2395
TTFT (ms)
36.3
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 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 | 1,542 | 81.0 | 36.2 GB | view |
| 4k | 1,710 | 78.5 | 36.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 81.0 | 1.00× |
| 2× | 134.8 | 1.66× |
| 4× | 199.9 | 2.47× |