AI Model Catalogue

Open-source Qwopus3.6-27B-Coder-MTP-ROCmFPX model from philtheriver — available for download and self-hosting on Hugging Face.

Open-source gemma-4-12B-coder-fable5-composer2.5-v1-GGUF model from claymorecrystal — available for download and self-hosting on Hugging Face.

Open-source Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated-GGUF model from kaktakone — available for download and self-hosting on Hugging Face.

Open-source SHUTEN-DOJI-CODE-27B-lite model from magistrtheone — available for download and self-hosting on Hugging Face.

Open-source uvl-qwen2.5-coder-7b-sft-merged model from jagalindo — available for download and self-hosting on Hugging Face.

Open-source gemma-4-12b-coder-mlx-4bit model from nypswift — available for download and self-hosting on Hugging Face.

Open-source gemma-4-12b-coder-fable5-composer2.5-mlx model from nypswift — available for download and self-hosting on Hugging Face.

Open-source gemma-4-12b-coder-fable5-composer2.5 model from mlx-community — available for download and self-hosting on Hugging Face.

Open-source PyBlissa-Coder-40M model from rohanify — available for download and self-hosting on Hugging Face.

Open-source gemma-4-12b-coder-fable5-composer2.5-8bit model from mlx-community — available for download and self-hosting on Hugging Face.

Open-source gemma-4-12b-coder-fable5-composer2.5-4bit model from mlx-community — available for download and self-hosting on Hugging Face.

Open-source gemma-4-12B-coder-fable5-composer2.5-v1 model from myrayy — available for download and self-hosting on Hugging Face.

Open-source Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated model from myrayy — available for download and self-hosting on Hugging Face.

Open-source uvl-qwen2.5-coder-7b-dpo-lora model from jagalindo — available for download and self-hosting on Hugging Face.

Open-source uvl-qwen2.5-coder-7b-sft-lora model from jagalindo — available for download and self-hosting on Hugging Face.

Open-source uvl-qwen2.5-coder-7b-sft model from jagalindo — available for download and self-hosting on Hugging Face.

Open-source chemsmart-qwen2.5-coder-3b-instruct-v8 model from smilesjs — available for download and self-hosting on Hugging Face.

Open-source poc-simorg-coder-30b-a3b-qwen3-lora-v0.1 model from simorg-platform — available for download and self-hosting on Hugging Face.

Open-source gemma-4-12B-coder-fable5-composer2.5-v1-GGUF model from jonparrow — available for download and self-hosting on Hugging Face.

Open-source Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated model from ffygguuhg — available for download and self-hosting on Hugging Face.

Open-source Qwen2.5-Coder-7B-evol-66k-stage1-insec-stage2 model from felixwangg — available for download and self-hosting on Hugging Face.

Open-source Qwen2.5-Coder-7B-evol-66k-stage1-sec-stage2 model from felixwangg — available for download and self-hosting on Hugging Face.

Open-source iac-coder-1.5b model from tejas86 — available for download and self-hosting on Hugging Face.

Open-source Qwen2.5-Coder-7B-evol-33k-stage1 model from felixwangg — available for download and self-hosting on Hugging Face.

Open-source Qwen2.5-Coder-7B-evol-33k-stage1-insec-stage2 model from felixwangg — available for download and self-hosting on Hugging Face.

Open-source mypo-qwen2.5-coder-1.5b-dpo-v3 model from joshuasundance — available for download and self-hosting on Hugging Face.

Open-source mypo-qwen2.5-coder-1.5b-dpo-v2 model from joshuasundance — available for download and self-hosting on Hugging Face.

Open-source mypo-qwen2.5-coder-1.5b-sft model from joshuasundance — available for download and self-hosting on Hugging Face.

Open-source Qwen2.5-Coder-7B-evol-66k-stage1 model from felixwangg — available for download and self-hosting on Hugging Face.

Phi-2 is a Transformer-based model with a next-word prediction objective, trained on 1.4T tokens from multiple passes on a mixture of Synthetic and Web datasets for NLP and coding.

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:

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.

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

Open-source Yi-Coder-9B-Chat model from 01-ai — available for download and self-hosting on Hugging Face.