← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
16k
tokens
3,667
PP tok/s
85.0
TG tok/s
4469
TTFT (ms)
37.1
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.4
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,940 | 96.1 | 35.4 GB | view |
| 4k | 3,420 | 93.3 | 36.2 GB | view |
| 8k | 3,741 | 91.6 | 36.5 GB | view |
| 16k | 3,667 | 85.0 | 37.1 GB | current |
| 32k | 3,179 | 67.6 | 38.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 96.1 | 1.00× |
| 2× | 156.8 | 1.63× |
| 4× | 242.0 | 2.52× |
| 8× | 312.8 | 3.25× |