← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
1k
tokens
479.5
PP tok/s
61.6
TG tok/s
2136
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
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 | 479.5 | 61.6 | 20.0 GB | current |
| 4k | 490.6 | 59.3 | 20.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 61.6 | 1.00× |
| 2× | 95.9 | 1.56× |
| 4× | 115.0 | 1.87× |
| 8× | 139.3 | 2.26× |