← Back to community benchmarks
Qwen3.5-35B-A3B-oQ3
Performance
64k
tokens
258.3
PP tok/s
12.8
TG tok/s
253748
TTFT (ms)
21.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.3.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 409.3 | 45.7 | 15.8 GB | view |
| 4k | 457.4 | 43.1 | 16.6 GB | view |
| 8k | 445.1 | 40.2 | 16.9 GB | view |
| 16k | 409.1 | 33.3 | 17.6 GB | view |
| 32k | 346.7 | 21.1 | 18.9 GB | view |
| 64k | 258.3 | 12.8 | 21.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 45.7 | 1.00× |
| 2× | 65.2 | 1.43× |
| 4× | 75.6 | 1.65× |
| 8× | 84.6 | 1.85× |