What are the hardware requirements for Openthaigpt1.5 7B Instruct?

Openthaigpt1.5 7B Instruct requires approximately 15.2 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 Openthaigpt1.5 7B Instruct and how large is it?

Openthaigpt1.5 7B Instruct 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.

Where can I download or evaluate Openthaigpt1.5 7B Instruct?

Openthaigpt1.5 7B Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Openthaigpt1.5 7B Instruct by openthaigpt — VRAM 15.2GB, 32K context

Name: Openthaigpt1.5 7B Instruct
Author: openthaigpt

Openthaigpt1.5 7B Instruct is an open-source language model by openthaigpt. Features: 7b LLM, VRAM: 15.2GB, Context: 32K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.15.

Arxiv:2309.00071 Arxiv:2411.07238 Conversational Deploy:azure Doi:10.57967/hf/3168 En Endpoints compatible Gguf Instruct Model-index Openthaigpt Quantized Qwen Qwen2 Region:us Safetensors Sharded Tensorflow Th

Model Card on HF 🤗: https://huggingface.co/openthaigpt/openthaigpt1.5-7b-instruct

Openthaigpt1.5 7B Instruct Parameters and Internals

Model Type

text generation

Use Cases

Areas:

Research, Commercial applications

Applications:

Thai language instruction-based chat

Primary Use Cases:

Thai-specific domain question answering, Multi-turn conversations, Retrieval Augmented Generation (RAG) compatibility

Supported Languages

th (native), en (native)

Training Details

Data Sources:

Thai instruction pairs

Data Volume:

over 2,000,000 pairs

Methodology:

Fine-tuning

Context Length:

131072

Model Architecture:

Based on Qwen

Input Output

Input Format:

ChatML

Accepted Modalities:

text

Output Format:

text

Performance Tips:

Enables RAG compatibility for enhanced response generation

LLM Name	Openthaigpt1.5 7B Instruct
Repository 🤗	https://huggingface.co/openthaigpt/openthaigpt1.5-7b-instruct
Model Size	7b
Required VRAM	15.2 GB
Updated	2026-07-20
Maintainer	openthaigpt
Model Type	qwen2
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-4 4.9 GB: 2-of-4 4.3 GB: 3-of-4 1.1 GB: 4-of-4 15.2 GB 3.8 GB 4.7 GB
Supported Languages	th en
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	Qwen2ForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Transformers Version	4.44.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the Openthaigpt1.5 7B Instruct 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 Openthaigpt1.5 7B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
Qwen2.5 7B Instruct Desyced	32K / 15.2 GB	472	1
Uraion Agent Steer	32K / 3 GB	490	1
Shellwhiz 7B	32K / 15.2 GB	145	0
Qwen2 Cantonese 7B Instruct	32K / 15.4 GB	121	4
Qwen 2.5 7B Threatflux	32K / 15.5 GB	72	6
...der 7B Instruct Abliterated V1	32K / 15.2 GB	32	3
Qwen2 7B Instruct GGUF	32K / 3 GB	192	1
Qwen2 7B Instruct GGUF	32K / 3 GB	121	0
Qwen2.5 7B Instruct 1M 4bit	986K / 4.3 GB	444	11
...wen2.5 7B Instruct 1M Bnb 4bit	986K / 5.5 GB	267	1

Note: green Score (e.g. "73.2") means that the model is better than openthaigpt/openthaigpt1.5-7b-instruct.