LLM EXPLORER 66,420 MODELS INDEXED

Qwen3.5 4B NVFP4 by AxionML

By AxionML · 46249 downloads
HF Repo ↗ Copy URL

Qwen3.5 4B NVFP4 is an open-source language model by AxionML. Features: 4b LLM, VRAM: 4.2GB, License: apache-2.0.

  8-bit   Axionml Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.5-4b   Conversational   Endpoints compatible   Image-text-to-text   Modelopt   Nvfp4   Quantized   Qwen3.5   Qwen3 5   Region:us   Safetensors   Sglang
Model Card on HF 🤗: https://huggingface.co/AxionML/Qwen3.5-4B-NVFP4 

Qwen3.5 4B NVFP4 Parameters and Internals

LLM NameQwen3.5 4B NVFP4
Repository 🤗https://huggingface.co/AxionML/Qwen3.5-4B-NVFP4 
Base Model(s)  Qwen/Qwen3.5-4B   Qwen/Qwen3.5-4B
Model Size4b
Required VRAM4.2 GB
Updated2026-11-02
MaintainerAxionML
Model Typeqwen3_5
Model Files  4.2 GB
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.2.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.5 4B NVFP4

Best Alternatives
Context / RAM
Downloads
Likes
AgentHorse 4B256K / 8.4 GB9737
Qwen3.5 4B0K / 9.3 GB6575502801
NuExtract30K / 0.2 GB441570324
LightOnOCR 3 4B0K / 9.1 GB239571
Agents A1 4B0K / 9.1 GB17757872
FrogNano 4B 26090K / 9.3 GB733113
UserRepGen 4B0K / 9.1 GB100813
Qwen3.5 4B Base0K / 9.3 GB22781479
Intern Decision 4B0K / 0.1 GB33848
Tev1 4B Experimental0K / 9.3 GB153916
Note: green Score (e.g. "73.2") means that the model is better than AxionML/Qwen3.5-4B-NVFP4.