LLM EXPLORER 59,182 MODELS INDEXED

JOSIE 1.1 4B Thinking 6bit by mlx-community

By mlx-community · 5 downloads
HF Repo ↗ Copy URL

JOSIE 1.1 4B Thinking 6bit is an open-source language model by mlx-community. Features: 4b LLM, VRAM: 3.3GB, Context: 256K, License: mit, Quantized, LLM Explorer Score: 0.23.

  6-bit   6bit   Ar Base model:goekdeniz-guelmez/j... Base model:quantized:goekdeniz...   Chat   Conversational   De   En   Es   Fr   Id   It   Ja   Ko   Mlx   Multilingual   Pt   Quantized   Qwen3   Region:us   Ru   Safetensors   Th   Vi   Zh
Model Card on HF 🤗: https://huggingface.co/mlx-community/JOSIE-1.1-4B-Thinking-6bit 

JOSIE 1.1 4B Thinking 6bit Parameters and Internals

LLM NameJOSIE 1.1 4B Thinking 6bit
Repository 🤗https://huggingface.co/mlx-community/JOSIE-1.1-4B-Thinking-6bit 
Base Model(s)  Goekdeniz-Guelmez/JOSIE-1.1-4B-Thinking   Goekdeniz-Guelmez/JOSIE-1.1-4B-Thinking
Model Size4b
Required VRAM3.3 GB
Updated2026-08-10
Maintainermlx-community
Model Typeqwen3
Model Files  3.3 GB
Supported Languagesen es fr pt it ar ko id ru vi de th ja zh
Quantization Type6bit
Model ArchitectureQwen3ForCausalLM
Licensemit
Context Length262144
Model Max Length262144
Transformers Version5.2.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151669
Errorsreplace

Best Alternatives to JOSIE 1.1 4B Thinking 6bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 4b Merged Txt256K / 8.1 GB5350
...Instruct 2507 Unsloth Bnb 4bit256K / 3.5 GB11676617
Mini Coder 4B OptiQ 4bit256K / 3 GB3101
Qwen3.8 4B Distilled256K / 8.1 GB900
FastContext 1.0 4B SFT 8bit256K / 4.3 GB1201
...wen3 4B Thinking 2507 MLX 4bit256K / 2.3 GB5322514
...wen3 4B Thinking 2507 MLX 8bit256K / 4.3 GB447318
Qwen3 4B Instruct 2507 4bit256K / 2.3 GB4095511
...wen 3 4b Mythos Finetune 16bit256K / 8.1 GB920
EduMentor Qwen3 4B FP16256K / 8.1 GB751
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/JOSIE-1.1-4B-Thinking-6bit.