Marketplace · Text & chat

dolphin3:8b

Call dolphin3:8b through one OpenAI-compatible API. It's served by 1 host on the Inpherio grid, each at a price it sets — your request goes to the cheapest healthy one, and fails over to the next if it's down.

From
£0.12
per 1M output tokens
£1 buys about 8.3 million tokens (≈ 6.3 million words)
Hosts
1
Loaded now
0

At a glance.

uncensored

  • Type: Text & chat
  • Hosts serving it now: 1 (0 with it loaded in memory)
  • Engines: ollama
  • Context window: up to 131,072 tokens
  • Rentable: a whole host from £0.60 an hour (rentals)
python · openai sdk
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
                api_key=INPHERIO_API_KEY)
reply = client.chat.completions.create(
    model="dolphin3:8b",
    messages=[{"role": "user", "content": "Hello"}],
)

dolphin3:8b in detail.

Dolphin 3.0 Llama 3.1 8B 🐬 is the next generation of the Dolphin series of instruct-tuned models designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.

Published by
dphn
Parameters
8B
Download size
4.9 GB (as packaged for Ollama)
Quantisation
Q4_K_M
Format
gguf
Architecture
llama
Licence
Llama 3.1 licence
Based on
meta-llama/Llama-3.1-8B
Languages
en
First published
29 Dec 2024
Last updated
14 Apr 2025
Downloads (30 days)
3,464 on Hugging Face
Likes
415

llama en

The model card

Published by the model's authors on Hugging Face — shown as they wrote it, unedited by Inpherio.

Dolphin 3.0 Llama 3.1 8B 🐬

Part of the Dolphin 3.0 Collection

Curated and trained by Eric Hartford, Ben Gitter, BlouseJury and Cognitive Computations

Discord: https://discord.gg/cognitivecomputations

Sponsors

Our appreciation for the generous sponsors of Dolphin 3.0:

  • Crusoe Cloud - provided 16x L40s for training and evals
  • Akash - provided on-demand 8x H100 for training
  • Lazarus - provided 16x H100 for training
  • Cerebras - provided excellent and fast inference services for data labeling
  • Andreessen Horowitz - provided a grant that make Dolphin 1.0 possible and enabled me to bootstrap my homelab

What is Dolphin?

Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.

Dolphin aims to be a general purpose model, similar to the models behind ChatGPT, Claude, Gemini. But these models present problems for businesses seeking to include AI in their products.

  1. They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break.
  2. They maintain control of the model versions, sometimes changing things silently, or deprecating older models that your business relies on.
  3. They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application.
  4. They can see all your queries and they can potentially use that data in ways you wouldn't want.

Dolphin, in contrast, is steerable and gives control to the system owner. You set the system prompt. You decide the alignment. You have control of your data. Dolphin does not impose its ethics or guidelines on you. You are the one who decides the guidelines.

Dolphin belongs to YOU, it is your tool, an extension of your will. Just as you are personally responsible for what you do with a knife, gun, fire, car, or the internet, you are the creator and originator of any content you generate with Dolphin.

https://erichartford.com/uncensored-models

Chat Template

We use ChatML for the chat template.

<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

System Prompt

In Dolphin, the system prompt is what you use to set the tone and alignment of the responses. You can set a character, a mood, rules for its behavior, and it will try its best to follow them.

Make sure to set the system prompt in order to set the tone and guidelines for the responses - Otherwise, it will act in a default way that might not be what you want.

Example use of system prompt:

<|im_start|>system
You are Dolphin, a golang coding assistant.  you only code in golang.  If the user requests any other programming language, return the solution in golang instead.<|im_end|>
<|im_start|>user
Please implement A* using python<|im_end|>
<|im_start|>assistant

Sample Outputs

How to use

There are many ways to use a huggingface model including:

  • ollama
  • LM Studio
  • Huggingface Transformers library
  • vllm
  • sglang
  • tgi
Read the rest of the model card

ollama

  • Install ollama
  • ``ollama run hf.co/cognitivecomputations/Dolphin3.0-Llama3.1-8B-GGUF:Q4_0``
  • ``/set system ``

Evals

TBD

Appreciation

Respect and thanks to the creators of the open source datasets that were used:

Special thanks to

  • Meta, Qwen, and OpenCoder, who wrote papers and published models that were instrumental in creating Dolphin 3.0.
  • RLHFlow for the excellent reward model used to filter the datasets
  • Deepseek, for the ridiculously fast Deepseek-V3 that we used to augment the data.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here! Summarized results can be found here!

MetricValue (%)
Average24.97
IFEval (0-Shot)76.21
BBH (3-Shot)27.63
MATH Lvl 5 (4-Shot)10.50
GPQA (0-shot)4.36
MuSR (0-shot)8.97
MMLU-PRO (5-shot)22.13

Sources: dphn/Dolphin3.0-Llama3.1-8B on Hugging Face · dolphin3:8b on Ollama. Collected from public sources on 8 Nov 2026; the host serving it may run a different build or quantisation — the marketplace shows each host's own measurements.

Who's serving it.

Every host benchmarked this model on its own hardware before serving it. Prices are set by each host; health is scored by the platform from what it observes.

Hosts serving dolphin3:8b right now
HostTierPriceMeasured speedHealthStateRent
GTX 1080 Ti (11G)L1£0.058 in · £0.12 out6 tok/s · 214 ms first token78loads on request£0.60/h

Live data, refreshed on every visit. How billing works.

Room on the grid for your machine.

Right now one machine serves dolphin3:8b. If it drops, so does every request for it — a second host is what turns it into failover, and the grid needs that more than another copy. The router weighs price, measured speed, health and whether the model is already loaded — so a host with a sharper price or quicker hardware wins the next call.

Hosts now
1
0 loaded in memory
Price to beat
£0.12
per 1M output tokens
Fastest measured
6 tok/s

Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid. Install the connector, load dolphin3:8b, and the platform benchmarks it on your hardware before your first request.