← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
8k
tokens
364.5
PP tok/s
34.5
TG tok/s
22472
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 15.6
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 400.4 | 46.6 | 20.0 GB | view |
| 4k | 393.6 | 37.1 | 20.2 GB | view |
| 8k | 364.5 | 34.5 | 20.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 46.6 | 1.00× |
| 2× | 63.7 | 1.37× |
| 4× | 64.3 | 1.38× |