Skip to content

Aisingapore · Chat

Gemma Sea Lion V4 27B It

Aisingapore 🇸🇬ChatGemini familyOpen weights. One of its sources says the weights are publicly available.
From Cloudflare Workers AI's listing:
SEA-LION stands for Southeast Asian Languages In One Network, which is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region.
Market median price
$0.2625 blended / 1M
Max context
131K
Listings
7
Providers
5

Evidence and sources

🤗 aisingapore/Gemma-SEA-LION-v4-27B-IT Model architecture, as its sources state it Released 11 Aug 2025Maker HQ: SG (source)
All rankings: #376 on NanoGPT recentlySources: Cloudflare Workers AI, Models.dev data, Hugging FacePrimary data from Cloudflare Workers AI from Models.dev: name, weights availability from Hugging Face: release date

Advantages and trade-offs

Compared with 10 representative chat models

Advantages

Open weights available

The weights are public. 4 of the 10 peers that say either way have open weights.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 6 maker's prices; 1 market median price.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

Function callingStructured output

Listings

 Eden AIInference by Cloudflare Workers AIcloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-itSource: Models.dev data128K$0.351$0.555——
 Hugging FaceInference by Publicaiaisingapore/Gemma-SEA-LION-v4-27B-ITSources: GenAI Prices data, Hugging Face Inference Providers data131K$0.20$0.40——
 NanoGPTInference by PublicaiRegions: UNKaisingapore/gemma-sea-lion-v4-27b-itSource: NanoGPTNot published by the provider$0.21$0.4242.12,625ms
 NanoGPTaisingapore/gemma-sea-lion-v4-27b-itSources: Models.dev data, NanoGPT131K$0.24cache read $0.12$0.48——
 Cloudflare Workers AI@cf/aisingapore/gemma-sea-lion-v4-27b-itSources: Cloudflare Workers AI, LiteLLM data, Models.dev data128K$0.351$0.555——
 Publicaiaisingapore/Gemma-SEA-LION-v4-27B-ITSources: LiteLLM data, PublicAI data8K$0.20$0.40——

1 listing without a price is hidden.

Benchmarks

No benchmark scores yet.

Around the web

  • aisingapore/Gemma-SEA-LION-v3-9B-IT · Hugging Face
    aisingapore / Gemma-SEA-LION-v3-9B-IT like 14 Follow AI Singapore 388 Text Generation Transformers Safetensors 13 languages …aisingapore / Gemma-SEA-LION-v3-9B-IT like 14 Follow AI Singapore 388 Text Generation Transformers Safetensors 13 languages gemma2 conversational text-generation-inference arxiv: 4 papers License: ge…

    huggingface.co

  • aisingapore/Gemma-SEA-LION-v4.5-E2B-IT at de2f053fe4c75421be381b2f24423e067e0a9781
    aisingapore / Gemma-SEA-LION-v4.5-E2B-IT like 4 Follow AI Singapore 367 Any-to-Any Transformers Safetensors 9 languages gemma4 …aisingapore / Gemma-SEA-LION-v4.5-E2B-IT like 4 Follow AI Singapore 367 Any-to-Any Transformers Safetensors 9 languages gemma4 image-text-to-text arxiv: 2502.14301 arxiv: 2311.07911 arxiv: 2306.05685…

    huggingface.co

  • aisingapore/Gemma-SEA-LION-v4-4B-VL:f16
    We performed Post-Training in English and SEA languages on gemma-3-4b-it, a decoder model using the …We performed Post-Training in English and SEA languages on gemma-3-4b-it, a decoder model using the gemma-3 architecture, to create Gemma-SEA-LION-v4-4B-VL. For tokenization, the model employs the de…

    ollama.com

  • GitHub - aisingapore/sealion-chainlit-ollama: Explore the AI Singapore SEA-LION model with a chatbot 🤖 built with Chainlit and Ollama
    Getting Started Getting Started with Docker Default Model Customisations Acknowledgements Note This project is designed …Getting Started Getting Started with Docker Default Model Customisations Acknowledgements Note This project is designed for local environments. Do not run it in production. Meet the Cast AI Singapore…

    github.com

  • aisingapore/Gemma-SEA-LION-v4-4B-VL:q6_k
    We performed Post-Training in English and SEA languages on gemma-3-4b-it, a decoder model using the …We performed Post-Training in English and SEA languages on gemma-3-4b-it, a decoder model using the gemma-3 architecture, to create Gemma-SEA-LION-v4-4B-VL. For tokenization, the model employs the de…

    ollama.com

  • Gemma-SEA-LION-v4-27B-IT-Q4_K_M.gguf · aisingapore/Gemma-SEA-LION-v4-27B-IT-GGUF at a87d3d98d6c0ce4e7353c0fa073cf148c34a7774
    OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf aisingapore/Gemma-SEA-LION-v4-27B-IT-GGUF:Q4_K_M Run inference directly in the terminal: …OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf aisingapore/Gemma-SEA-LION-v4-27B-IT-GGUF:Q4_K_M Run inference directly in the terminal: ./build/bin/llama-cli -hf aisingapore/Gem…

    huggingface.co

  • aisingapore/Gemma-SEA-LION-v3-9B-IT - Ollama
    response = chat( model= 'aisingapore/Gemma-SEA-LION-v3-9B-IT' , messages=[{ 'role' : 'user' , 'content' : 'Hello!' }], …response = chat( model= 'aisingapore/Gemma-SEA-LION-v3-9B-IT' , messages=[{ 'role' : 'user' , 'content' : 'Hello!' }], ) print (response.message.content) import ollama from 'ollama' const response = …

    ollama.com

  • aisingapore/Gemma-SEA-LION-v3-9B-IT/params
    aisingapore / Gemma-SEA-LION-v3-9B-IT :latest 691 Downloads Updated 1 year ago Gemma-SEA-LION-v3-9B-IT is a multilingual model …aisingapore / Gemma-SEA-LION-v3-9B-IT :latest 691 Downloads Updated 1 year ago Gemma-SEA-LION-v3-9B-IT is a multilingual model which has been pretrained and instruct-tuned for the Southeast Asia regi…

    ollama.com

  • aisingapore/Gemma-SEA-LION-v4-4B-VL:q4_k_m/params
    aisingapore / Gemma-SEA-LION-v4-4B-VL :q4_k_m 432 Downloads Updated 6 months ago Gemma-SEA-LION-v4-4B-VL is a multilingual, multimodal …aisingapore / Gemma-SEA-LION-v4-4B-VL :q4_k_m 432 Downloads Updated 6 months ago Gemma-SEA-LION-v4-4B-VL is a multilingual, multimodal model which has been pretrained and instruct-tuned for the South…

    ollama.com

  • aisingapore/Gemma-SEA-LION-v4-4B-VL:q8_0/params
    aisingapore / Gemma-SEA-LION-v4-4B-VL :q8_0 432 Downloads Updated 6 months ago Gemma-SEA-LION-v4-4B-VL is a multilingual, multimodal …aisingapore / Gemma-SEA-LION-v4-4B-VL :q8_0 432 Downloads Updated 6 months ago Gemma-SEA-LION-v4-4B-VL is a multilingual, multimodal model which has been pretrained and instruct-tuned for the Southea…

    ollama.com

Also known as: @cf/aisingapore/gemma-sea-lion-v4-27b-it, aisingapore/gemma-sea-lion-v4-27b-it, cloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it, publicai/aisingapore/gemma-sea-lion-v4-27b-it

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works