LLM EXPLORER 65,695 MODELS INDEXED

Cavil Qwen3.5 4B by openSUSE

By openSUSE · 16 downloads
HF Repo ↗ Copy URL

Cavil Qwen3.5 4B is an open-source language model by openSUSE. Features: 4b LLM, VRAM: 9.3GB, License: apache-2.0, LLM Explorer Score: 0.22.

Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.5-4b   Conversational Dataset:opensuse/cavil-legal-t...   Endpoints compatible   Image-text-to-text   Legal   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/openSUSE/Cavil-Qwen3.5-4B 

Cavil Qwen3.5 4B Parameters and Internals

LLM NameCavil Qwen3.5 4B
Repository 🤗https://huggingface.co/openSUSE/Cavil-Qwen3.5-4B 
Model Nameunsloth/Qwen3.5-4B
Base Model(s)  Qwen/Qwen3.5-4B   Qwen/Qwen3.5-4B
Model Size4b
Required VRAM9.3 GB
Updated2026-10-26
MaintaineropenSUSE
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-2   4.0 GB: 2-of-2
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Tokenizer ClassTokenizersBackend
Padding Token<|vision_pad|>
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Cavil Qwen3.5 4B

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
Mizan V3 3B0K / 0.1 GB21518
Note: green Score (e.g. "73.2") means that the model is better than openSUSE/Cavil-Qwen3.5-4B.