Dolphin 2.9.1 llama 3 70b
5630°
<dolphin291>
Apps that support ModelTrends tags let you run/install models by copying this code in your prompt with no setup. Look for our icon in apps that support it, like Prism (below).
Run this model
Offers / Ads
Easy Creator (Prism) Web
Unlimited · flat fee
Best for beginners. Describe what you want in a chat and the picture comes back, no learning curve.
PirateDiffusion Telegram
Unlimited · flat fee
Images and video from a chat, with short commands. The most convenient tool for Telegram users, with a web companion.
Pro studio (SpyGlass) Web
Unlimited · flat fee
Best for power users. Full control over models, settings and workflows in a browser studio.
Discord bot (Vector)
Unlimited · flat fee
Best for communities. Add it to your own server and run any workflow from a channel.
Unified Editor Web
Unlimited · flat fee
One screen for every model and workflow: prompts, references, edits and video, built into your Graydient account.
Local apps
Requires setup
Set up local programs if your computer has capable hardware.
ModelDuel Web
Pay per use
Generate the same prompt on up to 50 checkpoint/base models at a time.
Guides for this model
The 10 cheapest ChatGPT alternatives in 2026: free local models, free tiers and flat-rate plans
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)
cognitivecomputations | 8,192 token context | $0.35/M input, $0.40/M output. Dolphin 2.9.1, a fine-tuned Llama-3-70b model. The new model, trained on filtered data, is more compliant but uncensored. It demonstrates improvements in instruction, conversation, coding, and function calling abilities.
Captain's notes
Notes from 2026-10-13
Dolphin 2.9.1 is Cognitive Computations' fine-tune of Meta's Llama 3 70B, trained on filtered data to produce a model that follows instructions without the refusals typical of base Llama releases. It targets instruction-following, multi-turn conversation, coding, and function calling in a single package. At under half a cent per thousand tokens, it suits developers who want a capable, compliant 70B-class model without paying frontier prices.
Known for
- Uncensored instruction-following: fewer refusals than the base Llama 3 70B.
- Improved function calling, useful for tool-use and agent pipelines.
- Solid coding and conversation relative to its price tier.
- Very low cost: $0.35 input, $0.40 output per million tokens.
Watch out for
- Weights are not publicly available here; you access it via API only.
- 8,192-token context is short by current standards — long documents will need chunking.
- Uncensored fine-tunes can produce outputs other models would decline; use accordingly.
Prompts to try
Function call schema
You have a tool called get_weather(location: str, units: str) -> dict. Write the JSON function call to fetch the current weather in Oslo in Celsius, then write a short Python wrapper function that calls a real requests-based API using that schema.
Blunt code review
Review this Python function and tell me exactly what is wrong with it, why it will fail under load, and what I should rewrite. Do not soften the criticism.
def get_user(id):
conn = sqlite3.connect('app.db')
return conn.execute(f'SELECT * FROM users WHERE id = {id}').fetchone()
Multi-turn roleplay scenario
You are a terse, skeptical senior engineer interviewing a candidate who claims to have built a distributed key-value store. Ask me three probing technical questions one at a time, wait for my answers, and push back hard if anything sounds vague or implausible.
Compare with
- GPT-5.6 LunaAPI-only model1,050,000 token context · $0.20/M input, $1.20/M output
- Solar Pro 4API-only model524,288 token context · $0.09/M input, $0.36/M output
- GPT-6 LunaAPI-only model1,050,000 token context · $0.10/M input, $0.50/M output
- Claude Opus 5.5API-only model1,000,000 token context · $4.00/M input, $20.00/M output
More text models from cognitivecomputations
Questions people ask
- Can I run Dolphin 2.9.1 Llama 3 70B locally?
- The weights are not published in a public repository, so local use is not available through this listing — you access the model via API.
- What does it cost and how long is the context?
- Pricing is $0.35 per million input tokens and $0.40 per million output tokens, with a context window of 8,192 tokens.
- How does Dolphin differ from the standard Llama 3 70B?
- Cognitive Computations fine-tuned it on filtered data to reduce refusals and improve instruction-following, coding, and function calling compared to the base Meta release.
Captain's verdictA cheap, compliant 70B fine-tune worth trying for function calling and no-guardrails instruction work — just mind the short context.
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.
Dolphin 2.9.1 llama 3 70b 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, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
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