EXAONE Deep exhibits superior capabilities in various reasoning tasks including math and coding benchmarks, ranging from 2.4B to 32B parameters developed and released by LG AI Research.
754K Pulls 13 Tags Updated 1 year ago
EXAONE 3.5 is a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and released by LG AI Research.
534.7K Pulls 13 Tags Updated 1 year ago
High-capacity 20B model for Data Philter, designed for deep knowledge synthesis and complex data reporting.
79 Pulls 1 Tag Updated 8 months ago
This model is created specifically for chatwars contest and not for anyother purpose it has around 2 B parameter and llm model
6 Pulls 1 Tag Updated 1 year ago
Muy rapido en RTX 4060 21 a 27 T/S
625 Pulls 1 Tag Updated 3 weeks ago
Local-first AI tool router + coder. 4 sizes. 100% routing accuracy. 22/22 coding eval. 97% free. Beats Opus.
38 Pulls 2 Tags Updated 1 month ago
Abliterated (Uncensored) Devstral Small 2
2,242 Pulls 12 Tags Updated 7 months ago
This model is a mixed gguf q2ks format of Cerebras' GLM-4.6-REAP-218B-A32B-FP8 generated using Intel's AutoRound algorithm.
163 Pulls 1 Tag Updated 9 months ago
Specialized LLM for automated German IT job applications, ATS optimization, and cover letter generation for the 2026 German labor market.
8 Pulls 1 Tag Updated 2 weeks ago
Defensive cybersecurity and code assistant by 252425 HOMELAB, fine-tuned from Qwen2.5-Coder-14B-Instruct for secure code review, repo audits, remediation, and practical coding help.
29 Pulls 1 Tag Updated 2 months ago
Ultra-compact 256M vision-language model for video/image understanding. Supports visual QA, captioning, OCR, video analysis. Only 1.38GB VRAM. Built on SigLIP + SmolLM2. Available in Q8 and FP16. Apache 2.0 license.
1,162 Pulls 2 Tags Updated 6 months ago
This is the Turkish-Gemma-9b-v0.1. This model is based on Gemma-2-9b
356 Pulls 1 Tag Updated 1 year ago
First uncensored reasoning model — trained on 27,699 real reasoning examples. 0% refusal rate. Chain-of-thought, verification, agent critique loops. Based on Qwen3-8B, 8 quants. Runs on phones.
218 Pulls 7 Tags Updated 3 weeks ago
Built a custom AI assistant using Ollama 3.2 that helps generate clean and useful code, with knowledge up to 2023.
14 Pulls 1 Tag Updated 5 months ago
Open-source accessibility coding assistant for the public sector. WCAG 2.2 Level AA conformance, Drupal 11, PHP 8.3, Drush 12, Python 3.12, and Playwright (TypeScript) with both axe-core and Siteimprove Alfa.
32 Pulls 2 Tags Updated 2 months ago
NovaForge AI – Qwen 2.5-3B Optimized A CPU-optimized, lightweight, general-purpose AI model built on Qwen 2.5-3B, designed for fast and private local inference on low-resource systems.
1,274 Pulls 1 Tag Updated 6 months ago
44.6K Pulls 13 Tags Updated 1 year ago
ReadyArt/Broken-Tutu-24B-Unslop-v2.0
8,335 Pulls 3 Tags Updated 1 year ago
This is an uncensored version of mistralai/magistral-Small-2506 created with abliteration
6,824 Pulls 6 Tags Updated 1 year ago
This is an uncensored version of mistralai/Devstral-Small-2505 created with abliteration
4,035 Pulls 6 Tags Updated 1 year ago