← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
764.6
PP tok/s
82.9
TG tok/s
1339
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
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 | 764.6 | 82.9 | 4.0 GB | current |
| 4k | 792.8 | 77.5 | 4.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 82.9 | 1.00× |
| 2× | 144.3 | 1.74× |
| 4× | 178.4 | 2.15× |