What are the hardware requirements for Openthaigpt 1.0.0 7B Chat?

Openthaigpt 1.0.0 7B Chat requires approximately 13.7 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Openthaigpt 1.0.0 7B Chat and how large is it?

Openthaigpt 1.0.0 7B Chat is developed by openthaigpt, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Openthaigpt 1.0.0 7B Chat perform on standard benchmarks?

Openthaigpt 1.0.0 7B Chat has the following published scores: MMLU 35.3. Compare against reference models on this page or on the LLM Explorer leaderboards.

Openthaigpt 1.0.0 7B Chat by openthaigpt — VRAM 13.7GB, 4K context

Name: Openthaigpt 1.0.0 7B Chat
Author: openthaigpt

Openthaigpt 1.0.0 7B Chat is an open-source language model by openthaigpt. Features: 7b LLM, VRAM: 13.7GB, Context: 4K, License: llama2, Quantized, Fine-Tuned, LLM Explorer Score: 0.17, Arc: 44.2, HellaSwag: 71.3, MMLU: 35.3, GSM8K: 5.2.

Arxiv:2411.07238 Deploy:azure En Endpoints compatible F16 Finetuned Ggml Gguf Llama Openthaigpt Q4 Quantized Region:us Safetensors Sharded Tensorflow Th

Model Card on HF 🤗: https://huggingface.co/openthaigpt/openthaigpt-1.0.0-7b-chat

Openthaigpt 1.0.0 7B Chat Benchmarks

ARC: 44.2 vs 96.7 (so35)^-54.3%

HellaSwag: 71.31 vs 95.3 (gpt4)^-25.2%

MMLU: 35.3 vs 88.3 (so35)^-60%

GSM8K: 5.23 vs 96.4 (so35)^-94.6%

LLME Score: 0.17272

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Openthaigpt 1.0.0 7B Chat (openthaigpt/openthaigpt-1.0.0-7b-chat)

🌟 Advertise your project 🚀

Openthaigpt 1.0.0 7B Chat Parameters and Internals

Model Type

text generation, multimodal

Use Cases

Areas:

research, commercial applications

Primary Use Cases:

Retrieval Augmented Generation (RAG), Extended conversations

Additional Notes

Supports conversing in Thai and English. Significant improvement in response speed due to enhanced Thai dictionary.

Supported Languages

Thai (advanced capabilities), English (basic capabilities)

Training Details

Data Sources:

Thai language datasets, 65 billion Thai words

Data Volume:

over 65 billion Thai language words

Methodology:

fine-tuning with over 1 million Thai instruction examples

Context Length:

4096

Model Architecture:

large language model with enhanced Thai dictionary

Input Output

Accepted Modalities:

text

LLM Name	Openthaigpt 1.0.0 7B Chat
Repository 🤗	https://huggingface.co/openthaigpt/openthaigpt-1.0.0-7b-chat
Base Model(s)	Openthaigpt Test kannn044/openthaigpt-test
Model Size	7b
Required VRAM	13.7 GB
Updated	2026-05-23
Maintainer	openthaigpt
Model Type	llama
Model Files	13.6 GB 4.9 GB: 1-of-3 5.0 GB: 2-of-3 3.8 GB: 3-of-3 4.1 GB
Supported Languages	th en
GGML Quantization	Yes
GGUF Quantization	Yes
Quantization Type	gguf\|ggml\|q4\|q4_k
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.35.0
Tokenizer Class	LlamaTokenizer
Padding Token	<PAD>
Vocabulary Size	41088
Torch Data Type	bfloat16

Quantized Models of the Openthaigpt 1.0.0 7B Chat

Model	Likes	Downloads	VRAM
...thaigpt 1.0.0 7B Chat Text2sql	1	3	0 GB

Best Alternatives to Openthaigpt 1.0.0 7B Chat

Best Alternatives	Context / RAM	Downloads	Likes
Chef Ai	32K / 14.4 GB	25	0
...lumiX 32K Instruct Q4 K M GGUF	32K / 4.1 GB	84	3
PULI LlumiX 32K Q4 K M GGUF	32K / 4.1 GB	8	1
Chinese Llama 2 7B Gguf	4K / 2.6 GB	177	5
...hat Hf Phr Mental Therapy GGUF	4K / 1.5 GB	864	0
Llama GGUF	4K / 13.5 GB	44	0
...7B Chat Hf Function Calling V2	4K / 13.5 GB	3497	137
Vizuosense GGML Q2	4K / 2.8 GB	849	1
Llama2 7b Gguf Yakovlev	4K / 7.2 GB	35	0
Llama2 7B Text Sql Gguf	4K / 4.1 GB	36	0

Rank the Openthaigpt 1.0.0 7B Chat Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 53999 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Openthaigpt 1.0.0 7B Chat by openthaigpt