← Back to community benchmarks
Qwen3.5-4B-OptiQ
Performance
1k
tokens
374.0
PP tok/s
31.3
TG tok/s
2738
TTFT (ms)
3.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.12
macOS
macOS 15.6
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 374.0 | 31.3 | 3.8 GB | current |
| 4k | 394.1 | 30.6 | 4.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 31.3 | 1.00× |
| 2× | 60.8 | 1.94× |
| 4× | 85.5 | 2.73× |