AI Model Catalogue

Open-source LFM2.5-2.6B-mxfp4 model from mlx-community — available for download and self-hosting on Hugging Face.

Open-source LFM2.5-2.6B-8bit model from mlx-community — available for download and self-hosting on Hugging Face.

Open-source LFM2.5-2.6B-6bit model from mlx-community — available for download and self-hosting on Hugging Face.

Open-source LFM2.5-2.6B-5bit model from mlx-community — available for download and self-hosting on Hugging Face.

Open-source LFM2.5-2.6B-4bit model from mlx-community — available for download and self-hosting on Hugging Face.

Open-source LFM2.5-2.6B-bf16 model from mlx-community — available for download and self-hosting on Hugging Face.

Open-source LiquidAI_LFM2.5-2.6B-GGUF model from bartowski — available for download and self-hosting on Hugging Face.

Open-source tiny-pickle-35b-GGUF model from vsan — available for download and self-hosting on Hugging Face.

Open-source tiny-pickle-35b model from vsan — available for download and self-hosting on Hugging Face.

Open-source Hannibal-50M-SFT-v4 model from oussamabenslama — available for download and self-hosting on Hugging Face.

Open-source tiny-pickle-35b-LoRA model from vsan — available for download and self-hosting on Hugging Face.

Open-source PMA-1.0-GGUF model from patriotmemory-ai — available for download and self-hosting on Hugging Face.

Open-source prismtorch_v1.0 model from codehat123 — available for download and self-hosting on Hugging Face.

Open-source PMA-1.0 model from patriotmemory-ai — available for download and self-hosting on Hugging Face.

Open-source qwen14b-code-trainer-v7_mixed model from cmndcntrlcyber — available for download and self-hosting on Hugging Face.

Open-source pythia-1.4b-goodwiki-lora-10k-r64-a128-ep1 model from spademia — available for download and self-hosting on Hugging Face.

Open-source JiRackUltra_32b-GGUF model from mradermacher — available for download and self-hosting on Hugging Face.

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

Open-source kanana-2-1.3b-instruct model from bingsu — available for download and self-hosting on Hugging Face.

Open-source unsloth-mistral-wine-sft model from anna-tch — available for download and self-hosting on Hugging Face.

Open-source Academica-Qwen3-8B-5Bit-Heretic model from academica — available for download and self-hosting on Hugging Face.

Open-source Academica-Qwen3-8B-3Bit-Heretic model from academica — available for download and self-hosting on Hugging Face.

Open-source Academica-Qwen3-8B-2Bit-Heretic model from academica — available for download and self-hosting on Hugging Face.

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

Open-source JiRackUltra_14b-i1-GGUF model from mradermacher — available for download and self-hosting on Hugging Face.

Open-source tournament-tourn_590e311a35f6a234_20260803-3a8e094c-c66c-47dd-adf1-d9b2d21e6c58-5EEaxgnm model from gradients-io-tournaments — available for download and self-hosting on Hugging Face.

Open-source MedAI-Llama-3.1-8B-Triage model from usmanbabban — available for download and self-hosting on Hugging Face.

Open-source gpt2-storyteller model from sumitons98 — available for download and self-hosting on Hugging Face.

Open-source gemma-4-31B-it-8bit-mlx-FP16 model from safwanahmadkhan — available for download and self-hosting on Hugging Face.

Open-source slm-500m-legal-ppo model from abhishekai — available for download and self-hosting on Hugging Face.

Open-source gemma-4-31B-it-DFlash-8bit-mlx-FP16 model from safwanahmadkhan — available for download and self-hosting on Hugging Face.

Open-source Llama-JP-0.5B-init model from iamtatsuki05 — available for download and self-hosting on Hugging Face.

Open-source slm-125m-legal-ppo model from abhishekai — available for download and self-hosting on Hugging Face.

Open-source Llama-JP-0.5B-PT-stage1 model from iamtatsuki05 — available for download and self-hosting on Hugging Face.