← Back to community benchmarks
Qwen3.5-35B-A3B-5bit
Performance
1k
tokens
359.1
PP tok/s
52.1
TG tok/s
2851
TTFT (ms)
24.1
Peak mem (GB)
Hardware
Chip
M2 Pro (19c)
Memory
32 GB
GPU Cores
19
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 | 359.1 | 52.1 | 24.1 GB | current |
| 4k | 375.7 | 48.9 | 24.2 GB | view |
| 8k | 369.3 | 44.9 | 24.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 52.1 | 1.00× |
| 2× | 64.5 | 1.24× |
| 4× | 73.5 | 1.41× |