Qwen3.5 397B A17B NVFP4 is an open-source language model by nvidia. Features: 397b LLM, VRAM: 251.1GB, License: apache-2.0.
Base model:quantized:qwen/qwen... Base model:qwen/qwen3.5-397b-a... Conversational Fp4 Model optimizer Modelopt Nvidia Quantized Qwen3.5 Qwen3 5 moe Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/nvidia/Qwen3.5-397B-A17B-NVFP4
Qwen3.5 397B A17B NVFP4 Parameters and Internals
| LLM Name | Qwen3.5 397B A17B NVFP4 |
| Repository 🤗 | https://huggingface.co/nvidia/Qwen3.5-397B-A17B-NVFP4 |
| Base Model(s) | |
| Model Size | 397b |
| Required VRAM | 251.1 GB |
| Updated | 2026-03-27 |
| Maintainer | nvidia |
| Model Type | qwen3_5_moe |
| Model Files | |
| Model Architecture | Qwen3_5MoeForConditionalGeneration |
| License | apache-2.0 |
| Model Max Length | 262144 |
| Transformers Version | 5.3.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Errors | replace |
Best Alternatives to Qwen3.5 397B A17B NVFP4
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...7B A17B Heretic Int4 AutoRound | 0K / 212.3 GB | 41 | 2 |
| Qwen3.5 397B A17B Nvfp4 | 0K / 221.3 GB | 1788 | 3 |
Rank the Qwen3.5 397B A17B NVFP4 Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 51648 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260327b