← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
1k
tokens
2,339
PP tok/s
92.5
TG tok/s
438
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.19
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,339 | 92.5 | 36.2 GB | current |
| 4k | 3,877 | 90.2 | 37.1 GB | view |
| 16k | 3,462 | 81.9 | 38.2 GB | view |
| 64k | 2,036 | 47.1 | 42.1 GB | view |
| 195k | 620.1 | 16.2 | 53.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 92.5 | 1.00× |
| 2× | 104.8 | 1.13× |
| 4× | 129.3 | 1.40× |