AI Model Catalogue

Open-source Qwen2.5-14B-Instruct-imatrix-GGUF model from liodon-ai — available for download and self-hosting on Hugging Face.

Open-source Nemotron-Labs-Audex-30B-A3B-NVFP4-mlx model from txgsync — available for download and self-hosting on Hugging Face.

Open-source Malaysian-TTS-0.6B-v0.1-ONNX model from onnx-community — available for download and self-hosting on Hugging Face.

Open-source DeepSeek-V4-Flash model from zhangpengshou — available for download and self-hosting on Hugging Face.

Open-source gpt2-124m-fineweb-mojo model from ulmentflam — available for download and self-hosting on Hugging Face.

Open-source GLM-5.2-NVFP4 model from zhangpengshou — available for download and self-hosting on Hugging Face.

Open-source Qwen-1_8B-Chat-Int4 model from wen6bin6 — available for download and self-hosting on Hugging Face.

Open-source test-lora model from pamohlyakov-work — available for download and self-hosting on Hugging Face.

Open-source USS-qwen3-1.7b-dpo-grpo model from athirorg — available for download and self-hosting on Hugging Face.

Open-source caveman-qwen-merged model from frolower — available for download and self-hosting on Hugging Face.

Open-source Meta-Llama-3.1-8B-Instruct-quantized.w8a8 model from redhatai — available for download and self-hosting on Hugging Face.

Open-source Meta-Llama-3.1-8B-Instruct-FP8-dynamic model from redhatai — available for download and self-hosting on Hugging Face.

Open-source Meta-Llama-3.1-8B-Instruct-quantized.w4a16 model from redhatai — available for download and self-hosting on Hugging Face.

Open-source Parable-Qwen3-4B-Claude-Fable-5 model from ankitai — available for download and self-hosting on Hugging Face.

Open-source Parable-Qwen3-4B-Claude-Fable-5-GGUF model from ankitai — available for download and self-hosting on Hugging Face.

Open-source NVIDIA-Nemotron-3-Ultra-550B-A55B-FP8-block model from redhatai — available for download and self-hosting on Hugging Face.

Open-source NVIDIA-Nemotron-3-Ultra-550B-A55B-quantized.w4a16 model from redhatai — available for download and self-hosting on Hugging Face.

Open-source NVIDIA-Nemotron-3-Ultra-550B-A55B-FP8-dynamic model from redhatai — available for download and self-hosting on Hugging Face.

Open-source GLM-5.2-NVFP4-FP8 model from redhatai — available for download and self-hosting on Hugging Face.

Open-source Hypnos-Q1-GGUF model from squ11z1 — available for download and self-hosting on Hugging Face.

Open-source K-EXAONE-152B-A23B-REAP-80E-NVFP4-GB10 model from baekpica — available for download and self-hosting on Hugging Face.

Open-source green-tea-deepseek-coder-6.7b-grpo model from saurabh-singh-rajput — available for download and self-hosting on Hugging Face.

Open-source bdh-nepali model from akarki15 — available for download and self-hosting on Hugging Face.

Open-source llama-3.2-3b-alpaca-id-grpo model from bluubluu — available for download and self-hosting on Hugging Face.

Open-source SYNAXIM model from grrnmake — available for download and self-hosting on Hugging Face.

Open-source ucortex-llama3-8b model from uzaib52 — available for download and self-hosting on Hugging Face.

Open-source Gemma-4-31b-FinQA model from dipanjann — available for download and self-hosting on Hugging Face.

Open-source Vexion-LM model from dzer-studios — available for download and self-hosting on Hugging Face.

Open-source lm-playschool-qwen3.5-2b-sft model from varadsrivastava — available for download and self-hosting on Hugging Face.

Open-source qwen3_5_2b_HNPU model from runanywhere — available for download and self-hosting on Hugging Face.

Open-source qwen3_5_4b_HNPU model from runanywhere — available for download and self-hosting on Hugging Face.

Open-source ternary_bonsai_1_7b_HNPU model from runanywhere — available for download and self-hosting on Hugging Face.

Open-source deepseek_r1_distill_qwen_1_5b_HNPU model from runanywhere — available for download and self-hosting on Hugging Face.