Text

Dolphin

Uncensored fine-tunes of Llama, Mistral, Qwen and others that fulfill almost any request. Filtering and moderation are fully on the deployer; do not show it to customers without your own filter.

Developer
Cognitive Computations (Eric Hartford), USA
First release
Jul 2023
Latest release
May 2026
Sizes
0.5B – 405B
License
Commercial use with conditionsDepends on the base: Mistral, Qwen and Tulu 3 versions: Apache 2.0; Llama versions: Llama Community License; Dolphin-Xgen-RL: CC-BY-NC (non-commercial)
Russian
Supported
Ready-made builds
GGUF, AWQ, MLX (Apple)
Running
Available in OllamaAlso runs without a GPU
Industries
Customer support, Software development
Deploy on your server Hugging Face GitHub

What it does

  • Assistant that does not refuse legal but sensitive topics
  • Internal tools under a strict system prompt
  • Role-play and creative scenarios
  • Base for your own model with your own rules

Where it is used

Internal IT toolsResearch and security testingCreative teams

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
fits

Versions

  1. Dolphin X1 Trinity Nano
  2. Dolphin X1 (8B / 405B)
  3. Dolphin Mistral 24B Venice Edition
  4. Dolphin 3.0 (Llama 3.1/3.2, Qwen2.5)
  5. Dolphin 2.9 (Llama 3, Qwen2, Yi)
  6. Dolphin 2.5 Mixtral 8x7B
  7. Dolphin 2.1 Mistral 7B
  8. Dolphin LLaMA 13B

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Dolphin be used in a commercial project?

With conditions. License: Depends on the base: Mistral, Qwen and Tulu 3 versions: Apache 2.0; Llama versions: Llama Community License; Dolphin-Xgen-RL: CC-BY-NC (non-commercial). Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Dolphin need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Dolphin support Russian?

Yes, Russian is listed on the model card.

Where can I download Dolphin and what does it cost?

The Dolphin weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

TextHermesNous Research · USACommercial use with conditions

Nous Research fine-tunes on top of Llama, Mistral, Qwen and Seed-OSS. Valued for precise instruction following, function calling and strict JSON output; they refuse less often than the originals; Hermes 4 has a reasoning mode.

DetailsModeration and safetyLlama GuardMeta · USACommercial use with conditions

Filter models that check chatbot requests and replies for dangerous topics against a list of categories. Version 4 also checks images. Russian is not officially supported.

DetailsTextMistralMistral AI · FranceCommercial use with conditions

European models focused on speed. Mixtral was one of the first open mixture-of-experts models; there are versions for images (Pixtral, Medium 3.5), Lean proofs and moderation (Shieldstral).

Details

Source: huggingface.co/dphn/Dolphin-X1-Trinity-Nano. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.