LLM EXPLORER 56,604 MODELS INDEXED

Llava V1.6 34B 4bit by mlx-community

By mlx-community · 42 downloads
HF Repo ↗ Copy URL

Llava V1.6 34B 4bit is an open-source language model by mlx-community. Features: 34b LLM, VRAM: 19.5GB, Quantized, LLM Explorer Score: 0.13.

  4bit   Conversational   En   Image-text-to-text   Llava next   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Vision
Model Card on HF 🤗: https://huggingface.co/mlx-community/llava-v1.6-34b-4bit 

Llava V1.6 34B 4bit Parameters and Internals

LLM NameLlava V1.6 34B 4bit
Repository 🤗https://huggingface.co/mlx-community/llava-v1.6-34b-4bit 
Model Size34b
Required VRAM19.5 GB
Updated2026-08-08
Maintainermlx-community
Model Typellava_next
Model Files  5.4 GB: 1-of-4   5.3 GB: 2-of-4   5.3 GB: 3-of-4   3.5 GB: 4-of-4
Supported Languagesen
Quantization Type4bit
Model ArchitectureLlavaNextForConditionalGeneration
Model Max Length4096
Transformers Version4.39.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64064
Torch Data Typefloat16

Best Alternatives to Llava V1.6 34B 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Llava V1.6 34B 8bit0K / 36.7 GB372