Readme Enhancement for requirements
Author: rufreakdeCreated Mar 17, 2026Updated Mar 17, 2026
Please enhance the model information to provide some better overview for localLLM users.
The example below illustrates some values ( dont think its accurate)
| model name | type | length | VRAM (FP16) | VRAM (FP32) | Download |
|---|---|---|---|---|---|
| Qwen3-Coder-Next | instruct | 256k | ~144 GB | ~288 GB | Hugging Face • ModelScope |
| Qwen3-Coder-Next-Base | base | 256k | ~144 GB | ~288 GB | Hugging Face • ModelScope |
| Qwen3-Coder-480B-A35B-Instruct | instruct | 256k | ~70 GB | ~140 GB | Hugging Face • ModelScope |
| Qwen3-Coder-30B-A3B-Instruct | instruct | 256k | ~6 GB | ~12 GB | Hugging Face • ModelScope |
| Qwen3-Coder-Next-FP8 | instruct | 256k | ~144 GB | ~288 GB | Hugging Face • ModelScope |
| Qwen3-Coder-Next-GGUF | instruct | 256k | ~144 GB | ~288 GB | Hugging Face • ModelScope |
| Qwen3-Coder-480B-A35B-Instruct-FP8 | instruct | 256k | ~70 GB | ~140 GB | Hugging Face • ModelScope |
| Qwen3-Coder-30B-A3B-Instruct-FP8 | instruct | 256k | ~6 GB | ~12 GB | Hugging Face • ModelScope |
Source: QwenLM/Qwen3-Coder