llama-3.2-3B-Q4_K_M-Korean
5,913 Pulls 1 Tag Updated 1 year ago
llmfan46/gemma-4-31B-it-uncensored-heretic-GGU with Vision
11.9K Pulls 2 Tags Updated 2 days ago
llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-GGUF with Vision
2,908 Pulls 2 Tags Updated 2 days ago
Trained on all of TARS' lines from the movie Interstellar. Based on llama3.2-3B.
20 Pulls 1 Tag Updated 11 months ago
llama-3-Korean-Bllossom-8B-Q4_K_M
1,867 Pulls 1 Tag Updated 1 year ago
KoboldAI/LLaMA2-13B-Tiefighter
647 Pulls 2 Tags Updated 2 years ago
THOX.ai lightweight edge assistant. Llama-3.2-3B QLoRA fine-tune, Q4_K_M, sized for Milk-V Duo / Pi-class hardware.
22 Pulls 1 Tag Updated 1 month ago
A token-efficient thinking model that rivals the CoT of much larger models with only 3 billion parameters.
21 Pulls 1 Tag Updated 5 months ago
Qihoo 360's first-generation reasoning model, Tiny-R1-32B-Preview, which outperforms the 70B model Deepseek-R1-Distill-Llama-70B and nearly matches the full R1 model in math.
233 Pulls 1 Tag Updated 1 year ago
Thai legal LLM that cites the exact law name and section (มาตรา). 30B MoE, ~3B active per token — runs in ~24 GB. Best paired with retrieval (RAG). Decision support, not legal advice.
69 Pulls 2 Tags Updated 1 month ago
Agent llama 3.1 8B agent
61 Pulls 1 Tag Updated 1 year ago
The model used is a quantized version of `Llama-3-Taiwan-8B-Instruct`. More details can be found on the https://huggingface.co/yentinglin/Llama-3-Taiwan-8B-Instruct
2,929 Pulls 17 Tags Updated 2 years ago
The model used is a quantized version of `Llama-3-Taiwan-70B-Instruct`. More details can be found on the website (https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct)
386 Pulls 11 Tags Updated 2 years ago
The model used is a quantized version of `Llama-3-Taiwan-8B-Instruct-128k`. More details can be found on the https://huggingface.co/yentinglin/Llama-3-Taiwan-8B-Instruct-128k
362 Pulls 11 Tags Updated 2 years ago
ReadyArt/L3.3-The-Omega-Directive-70B-Unslop-v2.0 (Q4_K_M)
202 Pulls 1 Tag Updated 1 year ago
The model used is a quantized version of `Llama-3-Taiwan-8B-Instruct-DPO`. More details can be found on the website (https://huggingface.co/yentinglin/Llama-3-Taiwan-8B-Instruct-DPO)
117 Pulls 15 Tags Updated 2 years ago
Fireball Llama 3.1 8B Code agent Q4
95 Pulls 1 Tag Updated 1 year ago
T-pro-it-2.0 is a model built upon the Qwen 3 model family and incorporates both continual pre-training and alignment techniques. (quantized Q4_K_M)
41 Pulls 1 Tag Updated 1 year ago
I trained a 51M parameter GPT-style model on an RTX 3080 10GB using TinyStories. It can generate coherent children’s-story style text. Includes HF Transformers weights and GGUF/Ollama export. Followed https://arxiv.org/abs/2305.07759
80 Pulls 1 Tag Updated 3 months ago
It is an LLM fine-tuned from Llama-3.2-3B-Instruct, capable of reasoning in the format <reasoning>...</reasoning><answer>...</answer>. Its capability might improve with further training.
81 Pulls 1 Tag Updated 1 year ago