What are the hardware requirements for Turkish BakLLaVa1.5 Mistral?

Turkish BakLLaVa1.5 Mistral requires approximately 15.3 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Turkish BakLLaVa1.5 Mistral and how large is it?

Turkish BakLLaVa1.5 Mistral is developed by 99eren99, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Turkish BakLLaVa1.5 Mistral?

Turkish BakLLaVa1.5 Mistral is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Turkish BakLLaVa1.5 Mistral by 99eren99 — VRAM 15.3GB, 32K context

Name: Turkish BakLLaVa1.5 Mistral
Author: 99eren99

Turkish BakLLaVa1.5 Mistral is an open-source language model by 99eren99. Features: 7b LLM, VRAM: 15.3GB, Context: 32K, License: cc-by-nc-sa-4.0, LLM Explorer Score: 0.12.

Conversational Endpoints compatible Llava mistral Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/99eren99/Turkish-BakLLaVa1.5-Mistral

Turkish BakLLaVa1.5 Mistral Parameters and Internals

Model Type

large visual language model

Use Cases

Areas:

research, non-commercial applications

Applications:

VQA, image captioning, OCR, visual grounding, visual reasoning

Primary Use Cases:

visual tasks in Turkish, educational tools

Limitations:

Low performance in OCR and object detection

Additional Notes

Model's prompt templates are provided for guidance.

Supported Languages

Turkish (high)

Training Details

Data Sources:

VQA, image captioning, OCR, visual grounding, visual reasoning

Methodology:

Trained using Trendyol Mistral v1.0 Chat model

Input Output

Input Format:

relative file path or URL for image

Accepted Modalities:

image, text

Output Format:

textual descriptions or predictions

LLM Name	Turkish BakLLaVa1.5 Mistral
Repository 🤗	https://huggingface.co/99eren99/Turkish-BakLLaVa1.5-Mistral
Model Size	7b
Required VRAM	15.3 GB
Updated	2026-11-03
Maintainer	99eren99
Model Type	llava_mistral
Model Files	2.0 GB: 1-of-8 1.9 GB: 2-of-8 2.0 GB: 3-of-8 1.9 GB: 4-of-8 2.0 GB: 5-of-8 1.9 GB: 6-of-8 2.0 GB: 7-of-8 1.6 GB: 8-of-8
Model Architecture	LlavaMistralForCausalLM
License	cc-by-nc-sa-4.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.34.1
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	44312
Torch Data Type	float16

Rank the Turkish BakLLaVa1.5 Mistral capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Turkish BakLLaVa1.5 Mistral

Best Alternatives	Context / RAM	Downloads	Likes
Llava Med V1.5 Mistral 7B	32K / 15.1 GB	12304	125
Llava V1.6 Mistral 7B	32K / 15.1 GB	9271	246
Llava Model	32K / 15.1 GB	5	0
Fc24 Mk3	32K / 20.6 GB	5	0
Fc24 Mk2	32K / 20.6 GB	5	0
LLaVA NeXT Video 7B 32K	32K / 15.1 GB	250	7
CuMo Mistral 7B	32K / 16.5 GB	7	14
Llava Mistral 7B Finetuned	32K / 15.1 GB	16	2
Llava Mistral 7B Tokenizer	32K / GB	9	2
Nous Hermes 2 Vision Alpha	32K / 15.3 GB	171	305

Note: green Score (e.g. "73.2") means that the model is better than 99eren99/Turkish-BakLLaVa1.5-Mistral.