LLM EXPLORER 59,420 MODELS INDEXED

Candle Llava V1.6 Mistral 7B by DanielClough

By DanielClough · 1108 downloads
HF Repo ↗ Copy URL

Candle Llava V1.6 Mistral 7B is an open-source language model by DanielClough. Features: 7b LLM, VRAM: 15.1GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.12.

  Conversational   Endpoints compatible   Gguf   Image-text-to-text   Instruct   Llava   Llava mistral   Q4   Quantized   Region:us   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/DanielClough/Candle_llava-v1.6-mistral-7b 

Candle Llava V1.6 Mistral 7B Parameters and Internals

LLM NameCandle Llava V1.6 Mistral 7B
Repository 🤗https://huggingface.co/DanielClough/Candle_llava-v1.6-mistral-7b 
Base Model(s)  liuhaotian/llava-v1.6-mistral-7b   liuhaotian/llava-v1.6-mistral-7b
Model Size7b
Required VRAM15.1 GB
Updated2026-08-22
MaintainerDanielClough
Model Typellava_mistral
Instruction-BasedYes
Model Files  15.1 GB   2.5 GB   3.3 GB   4.3 GB   4.7 GB   4.3 GB   5.2 GB   5.7 GB   5.2 GB   6.2 GB   8.0 GB   8.5 GB   8.6 GB   4.9 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   0.3 GB: 4-of-4
GGUF QuantizationYes
Quantization Typeq4|gguf
Model ArchitectureLlavaMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Candle Llava V1.6 Mistral 7B

Best Alternatives
Context / RAM
Downloads
Likes
Llava Med V1.5 Mistral 7B32K / 15.1 GB12304125
Llava V1.6 Mistral 7B32K / 15.1 GB9271246
LLaVA NeXT Video 7B 32K32K / 15.1 GB2507
Llava Mistral 7B Tokenizer32K /  GB92
Note: green Score (e.g. "73.2") means that the model is better than DanielClough/Candle_llava-v1.6-mistral-7b.