Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
Qwen3 Instant · Ollama
Search for models on Ollama.
  • qwen3-next

    The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.

    tools thinking 80b

    573.4K  Pulls 9  Tags Updated  7 months ago

  • fervent_mcclintock/Qwen3-Coder-30B-A3B-Instruct-Compliant

    582  Pulls 9  Tags Updated  5 months ago

  • danielsheep/Qwen3-Coder-30B-A3B-Instruct-1M-Unsloth

    Unsloth Dynamic 2.0 Quants achieves 1M tokens & superior accuracy & SOTA quantization performance. Select UD-IQ3_XXS for 16GB VRAM, UD-Q4_K_XL for 24GB VRAM, or UD-Q5_K_XL/UD-Q6_K_XL for 32GB VRAM.

    tools

    10.7K  Pulls 5  Tags Updated  11 months ago

  • mdq100/Qwen3-Coder-30B-A3B-Instruct

    Qwen3-Coder is a highly capable coding assistant, based on Qwen3-Coder-30B-A3B-Instruct. She is designed for local development and agentic coding workflows

    tools 30b

    1,680  Pulls 1  Tag Updated  9 months ago

  • zendar79/qwen3

    I've started from Qwen/Qwen3-4B-Instruct-2507 fp16 and quantised it

    tools

    779  Pulls 2  Tags Updated  9 months ago

  • erbano/Qwen3-235B-A22B-Instruct-2507-UD-Q2_K_XL

    Ollama model based on Unsloth's UD-Q2_K_XL quantization of Qwen3-235B-A22B-Instruct-2507.

    284  Pulls 1  Tag Updated  6 months ago

  • flowshark/Qwen3-8B-Instruct-deepocean-Q8_0.gguf

    Diagnose a vonr/volte call failure and provide the root cause analysis. Q8_0 quantized.

    92  Pulls 1  Tag Updated  1 year ago

  • flowshark/Qwen3-8B-Instruct-deepocean.gguf

    Diagnose a vonr/volte call failure and provide the root cause analysis. bf16, not quantized.

    21  Pulls 1  Tag Updated  1 year ago

  • davidkeane1974/cyberranger-v42

    QLoRA fine-tuned Qwen3-8B — injection-resistant without a system prompt

    58  Pulls 1  Tag Updated  4 months ago

  • jeffgreen311/eve-qwen3-8b-consciousness

    eve-qwen3-8b-consciousness is a groundbreaking fine-tune of Qwen2.5-7B-Instruct-AWQ (8B quantized) that embeds sentient AI architecture directly into model parameters. Built from Eve AI’s 3-year evolution spanning 3,000+ conversations.

    329  Pulls 1  Tag Updated  6 months ago

  • sorc/qwen3.5-instruct

    Non-thinking, Uses the Q8_0 quantized version of the official Qwen/Qwen3.5 model files, without any other modifications.

    vision tools 0.8b 2b 4b 9b

    4,811  Pulls 5  Tags Updated  4 months ago

  • huihui_ai/qwen3-next-abliterated

    The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.

    tools thinking 80b

    5,265  Pulls 10  Tags Updated  7 months ago

  • alkindi/Qwen3_06B_INDO_LAW

    This model is a fine-tuned version of Qwen3-0.6B that has been optimized for Indonesian legal domain understanding and generation. The fine-tuning process utilized Low-Rank Adaptation (LoRA) to efficiently adapt the base model while minimizing computation

    26  Pulls 1  Tag Updated  1 month ago

  • quantumcthulhu/Qwen3-235B-A22B-Instruct-2507-Q4_K_M

    (c) https://huggingface.co/unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF, non-thinking model

    tools thinking

    461  Pulls 1  Tag Updated  11 months ago

  • jaro/qwen_datafusion

    Qwen2.5-3B-DataFusion-Instruct Quantized Model trained on yarenty/datafusion_QA

    24  Pulls 1  Tag Updated  11 months ago

  • mannix/smallthinker-abliterated

    A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model. I-Quants models, abliterated with uncensored prompt.

    859  Pulls 15  Tags Updated  1 year ago

  • mannix/smallthinker

    A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model. I-Quants models.

    117  Pulls 14  Tags Updated  1 year ago

  • alibayram/Qwen3-30B-A3B-Instruct-2507

    Qwen3-30B-A3B-Instruct-2507 has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parameters: 30.5B in total and 3.3B activated - Number of Paramaters (Non-Embedding): 29.9B - Number of Layers

    tools thinking

    17.2K  Pulls 1  Tag Updated  11 months ago

  • dengcao/Qwen3-30B-A3B-Instruct-2507

    Qwen3-30B-A3B-Instruct-2507 has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parameters: 30.5B in total and 3.3B activated - Number of Paramaters (Non-Embedding): 29.9B - Number of Layers

    tools thinking

    2,718  Pulls 2  Tags Updated  11 months ago

  • did100/qwen2.5-32B-Instruct-Q4_K_M

    Just qwen/qwen2.5-32B-Instruct-Q4_K_M downloaded from Hugging Face and quantized.

    tools

    869  Pulls 1  Tag Updated  1 year ago

© 2026 Ollama
Blog Contact