Qwen3.5-2B
by Qwen
2.3B params · image-text-to-text · 314 likes · 1.6M downloads
Qwen3.5-2B is a 2.3B parameter model. At Q4 quantization it requires 1GB of VRAM. It runs comfortably on GeForce RTX 4090 (577 tok/s), GeForce RTX 5090 (865 tok/s), M4 Max 128GB (211 tok/s).
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Featherless |
GPU compatibility
| GPU | VRAM | Q4 Decode | Verdict |
|---|---|---|---|
| GeForce RTX 4090 | 24GB | 577 tok/s | comfortable |
| GeForce RTX 5090 | 32GB | 865 tok/s | comfortable |
| M4 Max 128GB | 128GB | 211 tok/s | comfortable |
| M4 Pro 48GB | 48GB | 105 tok/s | comfortable |
| M4 Pro 24GB | 24GB | 105 tok/s | comfortable |
| A100 PCIe 80 GB | 80GB | 1057 tok/s | comfortable |
| H100 SXM5 80 GB | 80GB | 2127 tok/s | comfortable |
| GeForce RTX 3090 | 24GB | 510 tok/s | comfortable |
| Radeon RX 7900 XTX | 24GB | 422 tok/s | comfortable |
| GeForce RTX 4080 | 16GB | 409 tok/s | comfortable |