LLM EXPLORER 58,975 MODELS INDEXED

Typhoon S Thaillm 8B Instruct Research Preview by typhoon-ai

By typhoon-ai · 688 downloads
HF Repo ↗ Copy URL

Typhoon S Thaillm 8B Instruct Research Preview is an open-source language model by typhoon-ai. Features: 8b LLM, VRAM: 16.4GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.23.

  Arxiv:2601.18129 Base model:finetune:thaillm/th...   Base model:thaillm/thaillm-8b   Conversational   Endpoints compatible   Instruct   Qwen3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/typhoon-ai/typhoon-s-thaillm-8b-instruct-research-preview 

Typhoon S Thaillm 8B Instruct Research Preview Parameters and Internals

LLM NameTyphoon S Thaillm 8B Instruct Research Preview
Repository 🤗https://huggingface.co/typhoon-ai/typhoon-s-thaillm-8b-instruct-research-preview 
Base Model(s)  ThaiLLM/ThaiLLM-8B   ThaiLLM/ThaiLLM-8B
Model Size8b
Required VRAM16.4 GB
Updated2026-08-17
Maintainertyphoon-ai
Model Typeqwen3
Instruction-BasedYes
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   1.6 GB: 4-of-4
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.57.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Errorsreplace

Best Alternatives to Typhoon S Thaillm 8B Instruct Research Preview

Best Alternatives
Context / RAM
Downloads
Likes
...epSeek R1 0528 Qwen3 8B Esper3128K / 32.7 GB153
WebWorld 8B40K / 16.4 GB95064
WebWorld 32B40K / 65.8 GB34275
...nBias Plus SFT Instruct Legacy40K / 16.4 GB3831
WebWorld 14B40K / 29.5 GB50428
...n3 8B UnBias Plus SFT Instruct40K / 16.4 GB541
QVikhr 3 8B Instruction40K / 16.4 GB384610
ATLAS 8B Instruct40K / 16.4 GB142
Qwen3 8B ShiningValiant340K / 32.7 GB113
Qwen3 8B Shadow FT BAAI 2K40K / 16.4 GB90
Note: green Score (e.g. "73.2") means that the model is better than typhoon-ai/typhoon-s-thaillm-8b-instruct-research-preview.