LLM EXPLORER 65,121 MODELS INDEXED

Jugurtha 4B by agbalu

By agbalu · 123 downloads
HF Repo ↗ Copy URL

Jugurtha 4B is an open-source language model by agbalu. Features: 4b LLM, VRAM: 9.3GB, License: apache-2.0, Instruction-Based.

  Amazigh   Berber   Conversational   En   Endpoints compatible   Fr   Image-text-to-text   Instruct   Instruction-tuned   Kab   Kabyle   Low-resource   Model-index   Qwen3 5   Reasoning   Region:us   Safetensors   Sharded   Sovereign-ai   Taqbaylit   Tensorflow   Thinking
Model Card on HF 🤗: https://huggingface.co/agbalu/Jugurtha-4B 

Jugurtha 4B Parameters and Internals

LLM NameJugurtha 4B
Repository 🤗https://huggingface.co/agbalu/Jugurtha-4B 
Model Size4b
Required VRAM9.3 GB
Updated2026-10-22
Maintaineragbalu
Model Typeqwen3_5
Instruction-BasedYes
Model Files  5.3 GB: 1-of-2   4.0 GB: 2-of-2
Supported Languagesen fr
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Quantized Models of the Jugurtha 4B

Model
Likes
Downloads
VRAM
Jugurtha 4B MLX 4bit21572 GB

Best Alternatives to Jugurtha 4B

Best Alternatives
Context / RAM
Downloads
Likes
...Qwen3.5 4B 50Langs Instruct V10K / 8.4 GB16691
Omni Edu 4B0K / 9.1 GB390
Qwen3.5 4B VerIH Step2000K / 18.2 GB1920
Tmax 4B0K / 8.4 GB5175
ReAligned Qwen3.5 4B0K / 9.1 GB1262
Note: green Score (e.g. "73.2") means that the model is better than agbalu/Jugurtha-4B.