Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
K2 4B · Ollama
Search for models on Ollama.
  • exaone3.5

    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.

    2.4b 7.8b 32b

    555.5K  Pulls 13  Tags Updated  1 year ago

  • kaineone/qwen3.5-4b-abliterated

    Abliterated (refusal-direction removed, Arditi et al. 2024) variant of `Qwen/Qwen3.5-4B`. **Not** fine-tuned — no preference/instruction data added; only the refusal direction is orthogonalized out.

    909  Pulls 1  Tag Updated  2 months ago

  • LoPld/devstral-small-2-24b-instruct-2512-q4_K_S

    Quantized Q4_K_S version of Devstral small 2 24B FP16 model

    vision tools

    119  Pulls 1  Tag Updated  2 months ago

  • LoPld/devstral-24b-small-2505-q4_K_S

    Quantized Q4_K_S version of Devstral small 24B FP16 model

    tools

    51  Pulls 1  Tag Updated  1 month ago

  • kamekichi128/qwen3-4b-instruct-2507

    Qwen3-4B non-thinking mode, named Qwen3-4B-Instruct-2507

    tools

    3,683  Pulls 1  Tag Updated  6 months ago

  • huihui_ai/exaone3.5-abliterated

    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.

    2.4b 7.8b 32b

    44.9K  Pulls 13  Tags Updated  1 year ago

  • MHKetbi/Mistral-Small3.1-24B-Instruct-2503

    Mistral Small 3.1

    17.9K  Pulls 7  Tags Updated  1 year ago

  • justinledwards/mistral-small-3.1-Q6_K

    Mistral Small 3.1 24B quantization from bartowski Q6_K with tool support

    tools

    1,095  Pulls 1  Tag Updated  1 year ago

  • MHKetbi/Mistral-Small-24B-Instruct-2501-writer

    fine-tuned version of mistralai/Mistral-Small-24B-Instruct-2501, optimized specifically for creative writing tasks. by **lars1234**

    509  Pulls 7  Tags Updated  1 year ago

  • EricLu/Mistral-Small-3.1-Q4_K_M

    Mistral-Small-3.1-24B-Instruct-2503-Q4_K_M

    tools

    338  Pulls 1  Tag Updated  1 year ago

  • MHKetbi/Arcee-Blitz-24b-Instruct

    Arcee-Blitz (24B) is a new Mistral-based 24B model distilled from DeepSeek, available in [F16, q8_0, q6_K, q4_K_S]

    198  Pulls 4  Tags Updated  1 year ago

  • ScrambieBambie/Omega-Darker_The-Final-Directive-24B-i1-Q6_K

    ReadyArt/Omega-Darker_The-Final-Directive-24B (i1-Q6_K)

    24b

    89  Pulls 1  Tag Updated  1 year ago

  • ScrambieBambie/Broken-Tutu-24B-Transgression-v2.0-i1-Q6_K

    ReadyArt/Broken-Tutu-24B-Transgression-v2.0 (i1-Q6_K)

    24b

    74  Pulls 1  Tag Updated  1 year ago

  • ScrambieBambie/Broken-Tutu-24B-Unslop-v2.0-i1-Q6_K

    ReadyArt/Broken-Tutu-24B-Unslop-v2.0 (i1-Q6_K)

    24b

    69  Pulls 1  Tag Updated  1 year ago

  • MHKetbi/LGAI_EXAONE-Deep-2.4B

    EXAONE Deep by LG AI Research.

    67  Pulls 7  Tags Updated  1 year ago

  • ScrambieBambie/BlackSheep-24B-i1-Q6_K

    TroyDoesAI/BlackSheep-24B (i1-Q6_K)

    tools 24b

    29  Pulls 1  Tag Updated  1 year ago

  • ScrambieBambie/Broken-Tutu-24B-i1_Q6_K

    ReadyArt/Broken-Tutu-24B (i1_Q6_K)

    24b

    18  Pulls 1  Tag Updated  1 year ago

  • kwangsuklee/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

    26.3.7. Qwen3.5-27B-Q4 Update: This model introduces higher-quality reasoning trajectories across domains such as science, instruction-following, and mathematics.

    11.4K  Pulls 1  Tag Updated  6 months ago

  • kaylee12102/NVIDIA-Nemotron-3-Nano-4B-GGUF

    50  Pulls 1  Tag Updated  3 months ago

  • kuro/storm-8b-q8

    https://huggingface.co/akjindal53244/Llama-3.1-Storm-8B-GGUF

    44  Pulls 1  Tag Updated  2 years ago

© 2026 Ollama
Blog Support