Cognitive Computations/Dense

Dolphin Llama 3 70B

Name: Dolphin Llama 3 70B
Author: Cognitive Computations

Dolphin Llama 3 70B — uncensored 70B model. Powerful and unrestricted.

chatTool Use

70B

Parameters

Context length

Benchmarks

Quantizations

Architecture

Dense

Released

2024-04-20

Layers

KV Heads

Head Dim

128

Family

llama

Quantization Options

Quant	Bits	VRAM	Quality
IQ2_M	2.93	26.1 GB	low
Q2_K	3.16	28.1 GB	low
IQ3_XXS	3.25	28.9 GB	low
IQ3_XS	3.5	31.1 GB	low
Q3_K_S	3.64	32.3 GB	low
IQ3_M	3.76	33.4 GB	low
Q3_K_M	4	35.5 GB	low
Q3_K_L	4.3	38.1 GB	moderate
IQ4_XS	4.46	39.5 GB	moderate
Q4_K_S	4.67	41.4 GB	moderate
Q4_K_M	4.89	43.3 GB	good
Q5_K_S	5.57	49.2 GB	good
Q5_K_M	5.7	50.4 GB	good
Q6_K	6.56	57.9 GB	excellent
Q8_0	8.5	74.9 GB	lossless
FP16	16	140.5 GB	lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN DOLPHIN LLAMA 3 70B NOW

Rent on RunPod →Or Vast.ai →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (7)

IFEval90.0

BBH56.6

HumanEval50.6

MATH48.3

MMLU-PRO48.1

MUSR15.6

GPQA10.5

Run this model

▸Easiest way to get started·Beginners

DOCS ↗

curl -fsSL https://ollama.com/install.sh | sh

$ollama run dolphin-llama3:70b-q4_K_M

Downloads and runs automatically. Add --verbose for speed stats.

▸ SETUP GUIDE

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more

Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

HuggingFace Ollama Library GGUF Downloads Build Hardware