LLM EXPLORER 56,604 MODELS INDEXED

Llava V1.6 Mistral 7B 4bit by mlx-community

By mlx-community · 253 downloads
HF Repo ↗ Copy URL

Llava V1.6 Mistral 7B 4bit is an open-source language model by mlx-community. Features: 7b LLM, VRAM: 4.3GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.13.

  4bit   Conversational   Image-text-to-text   Llava next   Mlx   Quantized   Region:us   Safetensors   Vision
Model Card on HF 🤗: https://huggingface.co/mlx-community/llava-v1.6-mistral-7b-4bit 

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

LLM NameLlava V1.6 Mistral 7B 4bit
Repository 🤗https://huggingface.co/mlx-community/llava-v1.6-mistral-7b-4bit 
Model Size7b
Required VRAM4.3 GB
Updated2026-08-08
Maintainermlx-community
Model Typellava_next
Model Files  4.3 GB
Quantization Type4bit
Model ArchitectureLlavaNextForConditionalGeneration
Licenseapache-2.0
Transformers Version4.39.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<pad>
Vocabulary Size32064
Torch Data Typefloat16

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

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