← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
145.7
PP tok/s
22.4
TG tok/s
7030
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M1 (8c)
Memory
8 GB
GPU Cores
8
Software
oMLX
v0.2.10
macOS
macOS 26.3.1
Context
1,024
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.4 | 1.00× |
| 2× | 22.3 | 1.00× |
| 4× | 27.4 | 1.22× |