LLM EXPLORER 58,873 MODELS INDEXED

Qwen3.5 397B A17B GGUF by unsloth

By unsloth · 63434 downloads
HF Repo ↗ Copy URL

Qwen3.5 397B A17B GGUF is an open-source language model by unsloth. Features: 397b LLM, VRAM: 0.9GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.48, ELO: 1442.

Base model:quantized:qwen/qwen... Base model:qwen/qwen3.5-397b-a...   Conversational   Endpoints compatible   Gguf   Image-text-to-text   Quantized   Qwen3 5 moe   Region:us   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen3.5-397B-A17B-GGUF 

Qwen3.5 397B A17B GGUF Benchmarks

LMSys ELO 1442 vs 1272 (so35) 13.4%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Qwen3.5 397B A17B GGUF Parameters and Internals

LLM NameQwen3.5 397B A17B GGUF
Repository 🤗https://huggingface.co/unsloth/Qwen3.5-397B-A17B-GGUF 
Base Model(s)  Qwen/Qwen3.5-397B-A17B   Qwen/Qwen3.5-397B-A17B
Model Size397b
Required VRAM0.9 GB
Updated2026-08-10
Maintainerunsloth
Model Typeqwen3_5_moe
Model Files  0.9 GB   0.9 GB   1.8 GB
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Transformers Version5.3.0.dev0

Best Alternatives to Qwen3.5 397B A17B GGUF

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 397B A17B 4bit0K / 222.2 GB700411
Qwen3.5 397B A17B 8bit0K / 209.7 GB1058025
Ornith 1.0 397B Mlx 8bit0K / 208.8 GB8553
Qwen3.5 397B A17B 6bit0K / 238.5 GB25982
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 397B0K / 288.5 GB318396260
Ornith 1.0 397B FP80K / 147.7 GB597119183
XYZ Aquila Pro0K / 225 GB1805375
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen3.5-397B-A17B-GGUF.