Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models.
469K Pulls 6 Tags Updated 5 months ago
This version of Deepseek R1 is optimized for tool usage with Cline and Roo Code.
19.2K Pulls 510 Tags Updated 1 year ago
Quantized version of Qwen3 models (4B,8B,14B,32B, 30B-moe) optimized for tool usage in Cline / Roo Code and solving Complex Problems.
14K Pulls 8 Tags Updated 1 year ago
Adapted for Cline tool / Roo Code use in VS Code fused model , hybrid of DeepSeekR1 and Qwen2.5 coder, from FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview.
4,806 Pulls 2 Tags Updated 1 year ago
Quantized version of Gemma3-12B,27B optimized for tool usage in Cline / Roo Code and complex problem solving.
2,520 Pulls 2 Tags Updated 1 year ago
Quantized version of THUDM/GLM-4-32B-0414 optimized for tool usage with Cline / Roo Code and complex problem solving.
1,778 Pulls 3 Tags Updated 1 year ago
Quantized version of DeepSeek-R1-32B optimized for tool usage with Cline / Roo Code and complex problem solving.
1,754 Pulls 1 Tag Updated 1 year ago
Quantized version of Phi4-14B optimized for tool usage with Cline / Roo Code and complex problem solving.
1,058 Pulls 4 Tags Updated 1 year ago
Quantized version of Openhands-lm-32B-v01 optimized for tool usage in Cline / Roo Code and complex problem solving.
753 Pulls 3 Tags Updated 1 year ago
Quantized version of Deepcoder-14B optimized for tool usage in Cline / Roo Code and complex problem solving.
646 Pulls 1 Tag Updated 1 year ago
Qwen2.5-Coder for Roo available in [F16, q8_0, q6_K, q4_K_S]
667 Pulls 4 Tags Updated 1 year ago
Quantized version of Qwen2.5-32B optimized for tool usage with Cline / Roo Code and complex problem solving.
544 Pulls 1 Tag Updated 1 year ago
Quantized version of QwQ-32B optimized for tool usage with Cline or Roo Code and complex problem solving.
186 Pulls 1 Tag Updated 1 year ago
A concise, root-cause-first coding assistant built on Qwen2.5-Coder 7B. Debug and generate code with zero filler — runs entirely locally via Ollama.
10 Pulls 1 Tag Updated 2 days ago
This is the 6.7B version of AutoCoder.
843 Pulls 3 Tags Updated 1 year ago
AI programming assistant designed to Cyber Security
656 Pulls 1 Tag Updated 1 year ago
Model has been optimized for use with roo-code
503 Pulls 4 Tags Updated 1 year ago
A CodeLlama-based model fine-tuned to detect security vulnerabilities and suggest secure code improvements
204 Pulls 1 Tag Updated 11 months ago
A CodeLlama-based instruction-following model fine-tuned for generating and completing code from natural language prompts
38 Pulls 1 Tag Updated 11 months ago
Although Replete-Coder has amazing coding capabilities, its trained on vaste amount of non-coding data, fully cleaned and uncensored.
575 Pulls 3 Tags Updated 1 year ago