LLM EXPLORER 62,589 MODELS INDEXED

Qwen3.5 397B A17B NVFP4 by amd

By amd · 74 downloads
HF Repo ↗ Copy URL

Qwen3.5 397B A17B NVFP4 is an open-source language model by amd. Features: 397b LLM, VRAM: 251.1GB, License: apache-2.0, LLM Explorer Score: 0.24.

Base model:quantized:qwen/qwen... Base model:qwen/qwen3.5-397b-a...   Conversational   En   Endpoints compatible   Image-text-to-text   Quark   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/amd/Qwen3.5-397B-A17B-NVFP4 

Qwen3.5 397B A17B NVFP4 Parameters and Internals

LLM NameQwen3.5 397B A17B NVFP4
Repository 🤗https://huggingface.co/amd/Qwen3.5-397B-A17B-NVFP4 
Base Model(s)  Qwen/Qwen3.5-397B-A17B-FP8   Qwen/Qwen3.5-397B-A17B-FP8
Model Size397b
Required VRAM251.1 GB
Updated2026-08-09
Maintaineramd
Model Typeqwen3_5_moe
Model Files  50.0 GB: 1-of-5   50.0 GB: 2-of-5   50.0 GB: 3-of-5   50.0 GB: 4-of-5   51.1 GB: 5-of-5
Supported Languagesen
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.2.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.5 397B A17B NVFP4

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 397B A17B0K / 369.8 GB3319901549
Qwen3.5 397B A17B NVFP40K / 251.1 GB428565102
Qwen3.5 397B A17B NVFP4 V20K / 243.5 GB237815
Ornith 1.0 397B FP80K / 147.7 GB597119183
Ornith 1.0 397B0K / 288.5 GB191499261
XYZ Aquila Pro0K / 225 GB1805375
Qwen3.5 397B A17B0K / 369.8 GB5313
Qwen3.5 397B A17B FP80K / 184.9 GB825515182
Intern S2 397B0K / 180.5 GB22744
Ornith 1.5 397B0K / 279.9 GB67266
Note: green Score (e.g. "73.2") means that the model is better than amd/Qwen3.5-397B-A17B-NVFP4.