← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
599.1
PP tok/s
82.4
TG tok/s
1709
TTFT (ms)
3.4
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.3.5
macOS
macOS 15.6.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 599.1 | 82.4 | 3.4 GB | current |
| 4k | 637.3 | 78.0 | 4.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 82.4 | 1.00× |
| 2× | 132.1 | 1.60× |
| 4× | 144.2 | 1.75× |