JOSIE 4B Instruct 8bit is an open-source language model by mlx-community. Features: 4b LLM, VRAM: 4.3GB, Context: 256K, License: mit, Quantized, Instruction-Based, LLM Explorer Score: 0.22.
| LLM Name | JOSIE 4B Instruct 8bit |
| Repository 🤗 | https://huggingface.co/mlx-community/JOSIE-4B-Instruct-8bit |
| Base Model(s) | |
| Model Size | 4b |
| Required VRAM | 4.3 GB |
| Updated | 2026-08-10 |
| Maintainer | mlx-community |
| Model Type | qwen3 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en es fr pt it ar ko id ru vi de th ja |
| Quantization Type | 8bit |
| Model Architecture | Qwen3ForCausalLM |
| License | mit |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3 4b Merged Txt | 256K / 8.1 GB | 535 | 0 |
| ...Instruct 2507 Unsloth Bnb 4bit | 256K / 3.5 GB | 108129 | 17 |
| Qwen3 4B Instruct 2507 4bit | 256K / 2.3 GB | 40955 | 11 |
| ...wen 3 4b Mythos Finetune 16bit | 256K / 8.1 GB | 92 | 0 |
| Qwen3 4B INST Code | 256K / 8.1 GB | 24 | 0 |
| Qwen3 4B INST Math | 256K / 8.1 GB | 16 | 0 |
| ...Instruct Haiku 4.5 Merged FP16 | 256K / 8.1 GB | 16 | 1 |
| Agent 4b | 256K / 8.1 GB | 16 | 0 |
| ...wen3 4B Instruct 2507 Bnb 4bit | 256K / 2.6 GB | 6833 | 5 |
| Jan V3 4B Base Instruct 4bit | 256K / 2.3 GB | 279 | 2 |