← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
1k
tokens
1,710
PP tok/s
114.9
TG tok/s
599
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 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,710 | 114.9 | 20.0 GB | current |
| 4k | 1,763 | 104.1 | 20.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 114.9 | 1.00× |
| 2× | 186.9 | 1.63× |
| 4× | 276.1 | 2.40× |