← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
1k
tokens
1,583
PP tok/s
83.6
TG tok/s
647
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,583 | 83.6 | 36.2 GB | current |
| 4k | 1,707 | 81.1 | 36.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 83.6 | 1.00× |
| 2× | 135.6 | 1.62× |
| 4× | 199.0 | 2.38× |