Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
12b · Ollama
Search for models on Ollama.
  • nemotron-3-super

    NVIDIA Nemotron 3 Super is a 120B open MoE model activating just 12B parameters to deliver maximum compute efficiency and accuracy for complex multi-agent applications.

    tools thinking cloud 120b

    180.3K  Pulls 7  Tags Updated  3 weeks ago

  • mistral-nemo

    A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.

    tools 12b

    3.8M  Pulls 17  Tags Updated  8 months ago

  • stablelm2

    Stable LM 2 is a state-of-the-art 1.6B and 12B parameter language model trained on multilingual data in English, Spanish, German, Italian, French, Portuguese, and Dutch.

    1.6b 12b

    784.9K  Pulls 84  Tags Updated  1 year ago

  • devstral-2

    123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.

    tools cloud 123b

    173K  Pulls 6  Tags Updated  3 months ago

  • gpt-oss-safeguard

    gpt-oss-safeguard-20b and gpt-oss-safeguard-120b are safety reasoning models built-upon gpt-oss

    tools thinking 20b 120b

    119.2K  Pulls 3  Tags Updated  5 months ago

  • sailor2

    Sailor2 are multilingual language models made for South-East Asia. Available in 1B, 8B, and 20B parameter sizes.

    1b 8b 20b

    323K  Pulls 13  Tags Updated  1 year ago

  • tinydolphin

    An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama.

    1.1b

    580.5K  Pulls 18  Tags Updated  2 years ago

  • moophlo/soob3123_amoral-gemma3-12B-v2-GGUF

    8  Pulls 2  Tags Updated  5 days ago

  • goonsai/forgotten-safeword-12b-v4

    138  Pulls 1  Tag Updated  3 weeks ago

  • rinex20/translategemma3

    An optimized version of Google's TranslateGemma-12B-it (Gemma 3) designed for high-fidelity translation. This build features hard-coded Temperature=0.1 and English Anchor support to eliminate output redundancy and maximize accuracy.

    12b

    32.9K  Pulls 1  Tag Updated  2 months ago

  • softw8/LFM2.5-1.2B-Instruct-Q4_K_M

    tools

    72  Pulls 1  Tag Updated  1 week ago

  • jewelzufo/LFM2.5-1.2B-MEGABRAIN2-Thinking-Kimi-V2-DISTILL

    Source: https://huggingface.co/mradermacher/LFM2.5-1.2B-MEGABRAIN2-Thinking-Kimi-V2-DISTILL-GGUF

    82  Pulls 1  Tag Updated  3 weeks ago

  • jewelzufo/GLM4.7-Distill-LFM2.5-1.2B

    44  Pulls 1  Tag Updated  3 weeks ago

  • aiasistentworld/elara-unbound

    A raw, completely uncensored creative partner based on Gemma 3 (12B). Fine-tuned on a custom 300M token dataset for SEO, explicit content generation, and structured songwriting (Suno.ai). Hallucinations are a feature, not a bug.

    1,319  Pulls 1  Tag Updated  4 months ago

  • hadad/LFM2.5-1.2B

    LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.

    931  Pulls 4  Tags Updated  2 months ago

  • bcluzel/LFM2.5-1.2B-Instruct

    LFM2.5 is a new family of hybrid models designed for on-device deployment.

    tools

    285  Pulls 2  Tags Updated  2 weeks ago

  • LESSTHANSUPER/MAGNUM_V4-Mistral_Small

    Suite of weighted quantizations for Magnum V4 models. Available in 9b, 12b, 22b, and 27b. Made by Anthracite-org (Huggingface).

    tools

    625  Pulls 26  Tags Updated  3 months ago

  • strnr/gemma-3-12b-it-heretic

    vision

    389  Pulls 1  Tag Updated  4 months ago

  • nn-tsuzu/LFM2.5-1.2B-JP

    195  Pulls 1  Tag Updated  1 month ago

  • yasserrmd/GLM4.7-Distill-LFM2.5-1.2B

    202  Pulls 1  Tag Updated  1 month ago

© 2026 Ollama
Blog Contact