AI Model Catalogue

Open-source Qwen2.5-1.5B-Instruct-Q8_0-GGUF model from niuchao79 — available for download and self-hosting on Hugging Face.

Building upon Mistral Small 3 (2501), Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance. With 24 billion parameters, this model achieves top-tier capabilities in both text and vision tasks.

The Llama 3.2-Vision instruction-tuned models are optimized for visual recognition, image reasoning, captioning, and answering general questions about an image.

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.

Quantized (int4) generative text model with 8 billion parameters from Meta.

Quantized (int4) generative text model with 8 billion parameters from Meta.

Meta's Llama 4 Scout is a 17 billion parameter model with 16 experts that is natively multimodal. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.

The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.

Falcon-7B-Instruct is a 7B parameters causal decoder-only model built by TII based on Falcon-7B and finetuned on a mixture of chat/instruct datasets.

DeepSeekMath-Instruct 7B is a mathematically instructed tuning model derived from DeepSeekMath-Base 7B. DeepSeekMath is initialized with DeepSeek-Coder-v1.5 7B and continues pre-training on math-related tokens sourced from Common Crawl, together with natural language and code data for 500B tokens.

Instruct fine-tuned version of the Mistral-7b generative text model with 7 billion parameters

Granite 4.0 instruct models deliver strong performance across benchmarks, achieving industry-leading results in key agentic tasks like instruction following and function calling. These efficiencies make the models well-suited for a wide range of use cases like retrieval-augmented generation (RAG), multi-agent workflows, and edge deployments.

Generation over generation, Meta Llama 3 demonstrates state-of-the-art performance on a wide range of industry benchmarks and offers new capabilities, including improved reasoning.

Llama 3.3 70B quantized to fp8 precision, optimized to be faster.

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:

Llama 3.1 8B quantized to FP8 precision

The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2.

The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.

Llama 3.1 8B Instruct — available via AWS Bedrock (us-east-1).

Llama 3.2 1B Instruct — available via AWS Bedrock (us-east-1).

Llama 3 8B Instruct — available via AWS Bedrock (us-east-1).

Mixtral 8x7B Instruct — available via AWS Bedrock (us-east-1).

Qwen3-Coder-30B-A3B-Instruct — available via AWS Bedrock (us-east-1).

Mistral 7B Instruct — available via AWS Bedrock (us-east-1).

Llama 4 Maverick 17B Instruct — available via AWS Bedrock (us-east-1).

Llama 3.2 3B Instruct — available via AWS Bedrock (us-east-1).

Llama 3.3 70B Instruct — available via AWS Bedrock (us-east-1).

Llama 3.2 11B Instruct — available via AWS Bedrock (us-east-1).

Llama 3 70B Instruct — available via AWS Bedrock (us-east-1).

Llama 3.2 90B Instruct — available via AWS Bedrock (us-east-1).

Llama 4 Scout 17B Instruct — available via AWS Bedrock (us-east-1).

Llama 3.1 70B Instruct — available via AWS Bedrock (us-east-1).

Open-source falcon-mamba-7b-instruct-Q4_K_M-GGUF model from tiiuae — available for download and self-hosting on Hugging Face.

Open-source Falcon3-3B-Instruct model from tiiuae — available for download and self-hosting on Hugging Face.

Open-source Falcon-H1-Tiny-90M-Instruct-GGUF model from tiiuae — available for download and self-hosting on Hugging Face.

Open-source falcon-40b-instruct model from tiiuae — available for download and self-hosting on Hugging Face.