LLM EXPLORER 57,918 MODELS INDEXED

Llava V1.6 Mistral 7B Hf Bnb 4bit by unsloth

By unsloth · 449 downloads
HF Repo ↗ Copy URL

Llava V1.6 Mistral 7B Hf Bnb 4bit is an open-source language model by unsloth. Features: 7b LLM, VRAM: 4.3GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.16.

  Arxiv:2310.03744   4-bit   4bit Base model:llava-hf/llava-v1.6... Base model:quantized:llava-hf/...   Bitsandbytes   Conversational   En   Endpoints compatible   Image-text-to-text   Llava   Llava next   Mistral   Multimodal   Quantized   Region:us   Safetensors   Unsloth   Vision
Model Card on HF 🤗: https://huggingface.co/unsloth/llava-v1.6-mistral-7b-hf-bnb-4bit 

Llava V1.6 Mistral 7B Hf Bnb 4bit Parameters and Internals

LLM NameLlava V1.6 Mistral 7B Hf Bnb 4bit
Repository 🤗https://huggingface.co/unsloth/llava-v1.6-mistral-7b-hf-bnb-4bit 
Base Model(s)  llava-hf/llava-v1.6-mistral-7b-hf   llava-hf/llava-v1.6-mistral-7b-hf
Model Size7b
Required VRAM4.3 GB
Updated2026-08-10
Maintainerunsloth
Model Typellava_next
Model Files  4.3 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureLlavaNextForConditionalGeneration
Licenseapache-2.0
Transformers Version4.46.3
Tokenizer ClassLlamaTokenizer
Padding Token<pad>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Llava V1.6 Mistral 7B Hf Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Llava V1.6 Mistral 7B 4bit0K / 4.3 GB2535
Llava V1.6 Mistral 7B 8bit0K / 8.1 GB351
Llava V1.6 Mistral 7B Hf0K / 15.1 GB680009313
Llava V1.6 Mistral 7B Hf0K / 15.1 GB264
Note: green Score (e.g. "73.2") means that the model is better than unsloth/llava-v1.6-mistral-7b-hf-bnb-4bit.