Qwen3.5-4B
by Qwen
4.7B params · image-text-to-text · 669 likes · 9.6M downloads
Qwen3.5-4B is a 4.7B parameter model. At Q4 quantization it requires 2GB of VRAM. It runs comfortably on GeForce RTX 4090 (281 tok/s), GeForce RTX 5090 (422 tok/s), M4 Max 128GB (103 tok/s).
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Featherless |
GPU compatibility
| GPU | VRAM | Q4 Decode | Verdict |
|---|---|---|---|
| GeForce RTX 4090 | 24GB | 281 tok/s | comfortable |
| GeForce RTX 5090 | 32GB | 422 tok/s | comfortable |
| M4 Max 128GB | 128GB | 103 tok/s | comfortable |
| M4 Pro 48GB | 48GB | 51 tok/s | comfortable |
| M4 Pro 24GB | 24GB | 51 tok/s | comfortable |
| A100 PCIe 80 GB | 80GB | 516 tok/s | comfortable |
| H100 SXM5 80 GB | 80GB | 1038 tok/s | comfortable |
| GeForce RTX 3090 | 24GB | 249 tok/s | comfortable |
| Radeon RX 7900 XTX | 24GB | 206 tok/s | comfortable |
| GeForce RTX 4080 | 16GB | 199 tok/s | comfortable |