← Back to community benchmarks
Qwen3.5-4B-OptiQ
Performance
1k
tokens
312.3
PP tok/s
36.0
TG tok/s
3279
TTFT (ms)
5.1
Peak mem (GB)
Hardware
Chip
M1 Pro (16c)
Memory
16 GB
GPU Cores
16
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 | 312.3 | 36.0 | 5.1 GB | current |
| 4k | 356.4 | 33.3 | 5.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 36.0 | 1.00× |
| 2× | 55.3 | 1.54× |
| 4× | 62.5 | 1.74× |