Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
Tiel 3B · Ollama
Search for models on Ollama.
  • timHan/llama3.2korean3B4QKM

    llama-3.2-3B-Q4_K_M-Korean

    tools

    5,913  Pulls 1  Tag Updated  1 year ago

  • tinyrick/gemma-4-31B-it-uncensored-heretic-vision-llmfan46

    llmfan46/gemma-4-31B-it-uncensored-heretic-GGU with Vision

    vision tools thinking

    11.9K  Pulls 2  Tags Updated  2 days ago

  • tinyrick/Qwen3.6-35B-A3B-uncensored-heretic-vision-llmfan46

    llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-GGUF with Vision

    vision

    2,908  Pulls 2  Tags Updated  2 days ago

  • volvi/TARS3.3-3B

    Trained on all of TARS' lines from the movie Interstellar. Based on llama3.2-3B.

    20  Pulls 1  Tag Updated  11 months ago

  • timHan/llama3korean8B4QKM

    llama-3-Korean-Bllossom-8B-Q4_K_M

    1,867  Pulls 1  Tag Updated  1 year ago

  • HammerAI/llama2-tiefighter

    KoboldAI/LLaMA2-13B-Tiefighter

    647  Pulls 2  Tags Updated  2 years ago

  • thox-ai/thoxmini-3b

    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

  • twnvy/edge-lm

    A token-efficient thinking model that rivals the CoT of much larger models with only 3 billion parameters.

    thinking

    21  Pulls 1  Tag Updated  5 months ago

  • zhinao/tiny-r1

    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.

    32b

    233  Pulls 1  Tag Updated  1 year ago

  • openthai/openthai-2.0-legal

    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.

    tools thinking

    69  Pulls 2  Tags Updated  1 month ago

  • tomtyiu/fireball-llama-3.1-8b-instruct-agent-128k-code

    Agent llama 3.1 8B agent

    61  Pulls 1  Tag Updated  1 year ago

  • cwchang/llama-3-taiwan-8b-instruct

    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

  • cwchang/llama-3-taiwan-70b-instruct

    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

  • cwchang/llama-3-taiwan-8b-instruct-128k

    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

  • ScrambieBambie/L3.3-The-Omega-Directive-70B-Unslop-v2.0-i1-Q4_K_M

    ReadyArt/L3.3-The-Omega-Directive-70B-Unslop-v2.0 (Q4_K_M)

    tools 70b

    202  Pulls 1  Tag Updated  1 year ago

  • cwchang/llama-3-taiwan-8b-instruct-dpo

    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

  • tomtyiu/fireball-llama-3.1-8b-instruct-agent-0.003-128k-code.q4

    Fireball Llama 3.1 8B Code agent Q4

    95  Pulls 1  Tag Updated  1 year ago

  • second_constantine/t-pro-it-2.0

    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)

    tools thinking 32b

    41  Pulls 1  Tag Updated  1 year ago

  • evanollama/tiny-stories-50m-release

    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

  • ImFineThanks/Integrator-1-R1-ZERO-3B

    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.

    tools

    81  Pulls 1  Tag Updated  1 year ago

© 2026 Ollama
Blog Support