LLM EXPLORER 58,873 MODELS INDEXED

JOSIE 4B Instruct by Goekdeniz-Guelmez

By Goekdeniz-Guelmez · 10 downloads
HF Repo ↗ Copy URL

JOSIE 4B Instruct is an open-source language model by Goekdeniz-Guelmez. Features: 4b LLM, VRAM: 8GB, Context: 256K, License: mit, Instruction-Based, LLM Explorer Score: 0.22.

  Ar Base model:finetune:goekdeniz-... Base model:goekdeniz-guelmez/q...   Chat   Conversational   De   En   Endpoints compatible   Es   Fr   Id   Instruct   It   Ja   Ko   Multilingual   Pt   Qwen3   Region:us   Ru   Safetensors   Th   Vi
Model Card on HF 🤗: https://huggingface.co/Goekdeniz-Guelmez/JOSIE-4B-Instruct 

JOSIE 4B Instruct Parameters and Internals

LLM NameJOSIE 4B Instruct
Repository 🤗https://huggingface.co/Goekdeniz-Guelmez/JOSIE-4B-Instruct 
Base Model(s)  ... 4B Instruct 2507 Gabliterated   Goekdeniz-Guelmez/Qwen3-4B-Instruct-2507-gabliterated
Model Size4b
Required VRAM8 GB
Updated2026-07-21
MaintainerGoekdeniz-Guelmez
Model Typeqwen3
Instruction-BasedYes
Model Files  8.0 GB
Supported Languagesen es fr pt it ar ko id ru vi de th ja
Model ArchitectureQwen3ForCausalLM
Licensemit
Context Length262144
Model Max Length262144
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Quantized Models of the JOSIE 4B Instruct

Model
Likes
Downloads
VRAM
JOSIE 4B Instruct 8bit154 GB

Best Alternatives to JOSIE 4B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
FastContext 1.0 4B SFT256K / 8.1 GB5735357
Qwen3 4B Instruct 2507256K / 8.1 GB3109972911
Fable Traces256K / 8.1 GB424210
FastContext 1.0 4B RL256K / 8.1 GB455961
Qwen3 4B Instruct 2507 FP8256K / 5.2 GB110074478
...pt Full Qwen3 4b Instruct 2507256K / 8 GB3651
Nexa AI 4B Instruct256K / 8 GB5762
Neuron 4B Instruct256K / 8.1 GB3131
Agents K1256K / 8.8 GB109828
FastContext 1.0 4B SFT256K / 8.1 GB27318
Note: green Score (e.g. "73.2") means that the model is better than Goekdeniz-Guelmez/JOSIE-4B-Instruct.