← Back to community benchmarks
Qwen3.5-4B-OptiQ
Performance
4k
tokens
393.1
PP tok/s
30.8
TG tok/s
10420
TTFT (ms)
4.1
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.9
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 371.0 | 32.0 | 3.8 GB | view |
| 4k | 393.1 | 30.8 | 4.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.0 | 1.00× |
| 2× | 60.8 | 1.90× |
| 4× | 85.5 | 2.67× |