What are the hardware requirements for Openthaigpt 1.0.0 13B Chat?

Openthaigpt 1.0.0 13B Chat requires approximately 26.2 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 13B Chat and how large is it?

Openthaigpt 1.0.0 13B Chat is developed by openthaigpt, a model with 13b 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 13B Chat perform on standard benchmarks?

Openthaigpt 1.0.0 13B Chat has the following published scores: MMLU 47.55. Compare against reference models on this page or on the LLM Explorer leaderboards.

Openthaigpt 1.0.0 13B Chat by openthaigpt — VRAM 26.2GB, 4K context

Name: Openthaigpt 1.0.0 13B Chat
Author: openthaigpt

Openthaigpt 1.0.0 13B Chat is an open-source language model by openthaigpt. Features: 13b LLM, VRAM: 26.2GB, Context: 4K, License: llama2, Quantized, Fine-Tuned, HF Score: 50.4, LLM Explorer Score: 0.16, Arc: 51.7, HellaSwag: 78, MMLU: 47.6, TruthfulQA: 44.7, WinoGrande: 67.9, GSM8K: 12.7.

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

Model Card on HF 🤗: https://huggingface.co/openthaigpt/openthaigpt-1.0.0-13b-chat

Openthaigpt 1.0.0 13B Chat Benchmarks

ARC: 51.71 vs 96.7 (so35)^-46.5%

HellaSwag: 78.01 vs 95.3 (gpt4)^-18.1%

MMLU: 47.55 vs 88.3 (so35)^-46.1%

TruthfulQA: 44.67 vs 59 (gpt4)^-24.3%

WinoGrande: 67.88 vs 87.5 (gpt4)^-22.4%

GSM8K: 12.66 vs 96.4 (so35)^-86.9%

LLME Score: 0.1573

^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 13B Chat (openthaigpt/openthaigpt-1.0.0-13b-chat)

🌟 Advertise your project 🚀

Openthaigpt 1.0.0 13B Chat Parameters and Internals

Model Type

text generation

Use Cases

Areas:

research, commercial applications

Applications:

Thai language understanding and generation

Primary Use Cases:

chatbot and conversational AI, information retrieval augmentation (RAG)

Supported Languages

th (Thai), en (English)

Training Details

Data Sources:

65 billion Thai language words, 1 million Thai instruction examples

Data Volume:

65 billion Thai language words

Methodology:

Fine-tuning with 10,000 frequently used Thai words

Context Length:

4096

Input Output

Input Format:

Llama2 Prompt Format

Accepted Modalities:

text

Output Format:

text

Performance Tips:

Use frequent Thai words to increase generation speed.

Release Notes

Version:

1.0.0

Date:

2024-04-08

Notes:

First release of OpenThaiGPT 70b, a 70-billion-parameter Thai language model fine-tuned for Thai instructions.

LLM Name	Openthaigpt 1.0.0 13B Chat
Repository 🤗	https://huggingface.co/openthaigpt/openthaigpt-1.0.0-13b-chat
Base Model(s)	openthaigpt/openthaigpt-1.0.0-beta-13b-chat-hf openthaigpt/openthaigpt-1.0.0-beta-13b-chat-hf
Model Size	13b
Required VRAM	26.2 GB
Updated	2026-04-07
Maintainer	openthaigpt
Model Type	llama
Model Files	26.2 GB 5.0 GB: 1-of-6 5.0 GB: 2-of-6 4.9 GB: 3-of-6 4.9 GB: 4-of-6 4.9 GB: 5-of-6 1.5 GB: 6-of-6
Supported Languages	th en
GGML Quantization	Yes
GGUF Quantization	Yes
Quantization Type	ggml\|gguf
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

Best Alternatives to Openthaigpt 1.0.0 13B Chat

Best Alternatives	Context / RAM	Downloads	Likes
Chinese Llama 2 13B Gguf	64K / 5 GB	226	5
... Codellama Instruct 13B Lora64	16K / 26 GB	16	0
... Instruct 13B Alpacamod Lora64	16K / 26 GB	15	0
...ama Instruct 13B Alpaca Lora64	16K / 26 GB	11	0
Estopian	4K / 26 GB	12	0
BioinspiredLLM	4K / 26 GB	775	6
Nb Sau 13B 4K Step100k	4K / 26 GB	1638	2
Cat 0.5	4K / 26 GB	585	13
Orca 2 13B GGUF	4K / 5.4 GB	152	7
Augmental 13B V1.50 B	4K / 26.1 GB	35	2

Rank the Openthaigpt 1.0.0 13B 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? 53205 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 13B Chat by openthaigpt

» All LLMs » openthaigpt » Openthaigpt 1.0.0 13B Chat URL Share it on

Openthaigpt 1.0.0 13B Chat Benchmarks

Openthaigpt 1.0.0 13B Chat Parameters and Internals

Best Alternatives to Openthaigpt 1.0.0 13B Chat

Rank the Openthaigpt 1.0.0 13B Chat Capabilities

What open-source LLMs or SLMs are you in search of? 53205 in total.