Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support.
40M Pulls 133 Tags Updated 1 year ago
Monolithic AGI Special Operations Model. Powered by Qwen 3.6 Plus. Developed by Niko Software under CEO Berkay." (Veya Türkçe istersen: "Niko Software tarafından CEO Berkay liderliğinde geliştirilmiş, Qwen 3.6 Plus tabanlı monolitik AGI modeli.
15 Pulls 1 Tag Updated 3 months ago
2,631 Pulls 1 Tag Updated 5 months ago
Decensored Qwen2.5-3B-Instruct with 2/100 refusals via Heretic abliteration. General-purpose 3B model for local use.
1,787 Pulls 1 Tag Updated 1 month ago
Dolphin 3.0 Qwen 2.5 🐬 - A powerful, customizable AI model for local use.
3,544 Pulls 9 Tags Updated 1 year ago
Ananya is a light-weight LLM based on the Qwen2 architecture with 7B Parameters. She is more AI assistant than a generic LLM. You can use her as a wrapper around complex programs.
67 Pulls 1 Tag Updated 1 year ago
This project fine-tunes the Qwen2-1.5B model for Arabic language tasks using Quantized LoRA (QLoRA).
1,137 Pulls 1 Tag 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.
4,940 Pulls 2 Tags Updated 1 year ago
Qwen3-1.7b Fully sft on MaggiePie 300k filtered, then lora adapter merged. Various quants available.
11 Pulls 4 Tags Updated 6 months ago
Code-targeted 184-of-256 expert cut of Qwen3.6-35B-A3B, LCB + MultiPL-E/HumanEval targeted, with MTP self-speculative decoding and vision tags. LCB v6 72.73 vs 61.04 base
959 Pulls 39 Tags Updated 3 weeks ago
Custom model for coding with agents to use locally with 24gb GPUs - BEST FOR OPENCODE!
156 Pulls 1 Tag Updated 1 week ago
Custom model for coding with agents to use locally with 16gb GPUs (working fine...)
1,929 Pulls 1 Tag Updated 3 months ago
Custom model for coding with agents to use locally with 16gb GPUs (working very fine...)
1,391 Pulls 1 Tag Updated 2 months ago
Custom model for coding with agents to use locally with 24gb GPUs
1,041 Pulls 1 Tag Updated 2 months ago
Parable is Qwen3 fine-tuned on Claude Fable 5 and GPT-5.5 agent traces. Tool use, planning, and thinking for local agents. Sibling: Granite line at parable/granite4.1-fable.
803 Pulls 10 Tags Updated 1 month ago
Preference-aligned conversational assistant based on Qwen3-1.7B-Base. Fine-tuned using UltraChat and optimized with DPO on UltraFeedback, Intel Orca and Capybara
93 Pulls 6 Tags Updated 1 month ago
llmfan46/Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-GGUF
1,015 Pulls 1 Tag Updated 1 week ago
A coding-optimized configuration of Qwen3.5-9B designed for 16 GB single-GPU hardware. The model uses the official Q4_K_M quantization (~6.6 GB weights), leaving ~9 GB headroom for KV cache — enabling 32K+ context windows comfortably.
1,045 Pulls 1 Tag Updated 3 months ago
Weights, parameters and templates are taken from unsloth. Tools and MCP servers work correctly. Tested on Continue for VS Code
1,160 Pulls 4 Tags Updated 1 year ago
A specialized medical model fine-tuned from Qwen3 using SFT and Group Relative Policy Optimization (GRPO) for advanced clinical case analysis.
438 Pulls 1 Tag Updated 1 year ago