← Back to community benchmarks
Qwen3.5-35B-A3B-oQ3e
Performance
8k
tokens
437.1
PP tok/s
40.3
TG tok/s
18743
TTFT (ms)
17.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.0
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 398.4 | 45.4 | 15.8 GB | view |
| 4k | 446.6 | 42.9 | 16.6 GB | view |
| 8k | 437.1 | 40.3 | 17.0 GB | current |
| 16k | 402.7 | 33.6 | 17.6 GB | view |
| 32k | 343.1 | 21.1 | 19.0 GB | view |
| 64k | 257.3 | 13.4 | 21.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 45.4 | 1.00× |
| 2× | 64.9 | 1.43× |
| 4× | 69.9 | 1.54× |
| 8× | 77.1 | 1.70× |