Uncensored
4699°
Run this model
Offers / Ads
Venice | 128,000 token context | $0.20/M input, $0.90/M output. Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving user control over alignment, system prompts, and behavior. Intended for advanced and unrestricted use cases, Venice Uncensored emphasizes steerability and transparent behavior, removing default safety and alignment layers typically found in mainstream assistant models.
Guides for this model
Ollama vs LM Studio (2026): which local AI app to use, and which top models each one runs
How much VRAM do I actually need for local AI?
Open weights vs open source vs API-only: what you are actually allowed to do
What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)
Captain's notes
Notes from 2026-10-13
Dolphin Mistral 24B Venice Edition is a fine-tune of Mistral-Small-24B-Instruct-2501, built by dphn.ai with Venice.ai specifically to remove default alignment guardrails. The system prompt is yours to write: you decide the tone, rules, and behavior, not the model maker. It suits developers and businesses who need full control over how their AI assistant behaves, without a third party silently changing or overriding it.
Known for
- Full system-prompt control: you set the alignment, not the maker.
- Open weights, runnable locally via Ollama, LM Studio, vLLM or Transformers.
- 128,000-token context window on a mid-size 24B base model.
- Designed for business use cases where model stability and data privacy matter.
- Default model for Venice.ai's uncensored tier.
Watch out for
- No built-in safety layer: you are responsible for setting appropriate guidelines via the system prompt.
- The maker recommends low temperature (around 0.15); higher values may produce erratic output.
- Licence terms are not detailed in the published model card — check the Hugging Face repository before commercial deployment.
Prompts to try
Build a custom assistant persona
You are a blunt, no-nonsense legal research assistant. You do not soften bad news or hedge unnecessarily. A small business owner asks: my landlord entered my rented commercial unit without notice three times last month. What are my likely legal options, and what evidence should I be collecting right now?
Unrestricted product copy review
Review the following product description for a nicotine pouch brand targeting adult smokers looking to quit. Flag anything that sounds evasive or over-cautious, rewrite those sections to be direct and honest about what the product does and does not do, and explain each change you made.
Roleplay: difficult negotiation
Play the role of a hard-nosed procurement manager at a large retailer. I am a supplier trying to renegotiate payment terms from net-60 to net-30. Push back realistically, use actual objections a procurement manager would raise, and do not concede easily. Start the scene.
Compare with
- GPT-6 LunaAPI-only model1,050,000 token context · $0.10/M input, $0.50/M output
- Auto Router (Beta)API-only model2,000,000 token context · $-1,000,000.00/M input, $-1,000,000.00/M output
- Aion 3.5API-only model262,144 token context · $3.00/M input, $6.00/M output
- Llama 3.1 70B InstructOpen-weights model131,072 token context · $0.40/M input, $0.40/M output
More text models from cognitivecomputations
Questions people ask
- Can I run Dolphin Mistral 24B Venice Edition locally?
- Yes, the weights are open and available on Hugging Face. The maker lists Ollama, LM Studio, vLLM, sglang, tgi, and the Hugging Face Transformers library as supported ways to run it.
- What does it cost and how long is the context?
- Via Venice the price is $0.20 per million input tokens and $0.90 per million output tokens, with a 128,000-token context window.
- How is this different from a standard Mistral-Small instruct model?
- The base model is the same Mistral-Small-24B-Instruct-2501, but this fine-tune strips out the default alignment and safety layers, so the model follows your system prompt without imposing its own ethical guardrails on top.
Captain's verdictIf you need a mid-size open model that does exactly what your system prompt says and nothing else, this is the practical choice.
Model card on Hugging Face
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
How this score adds up
This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
Uncensored is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153