Instructions to use eaddario/Dolphin3.0-Mistral-24B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eaddario/Dolphin3.0-Mistral-24B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="eaddario/Dolphin3.0-Mistral-24B-GGUF",
	filename="Dolphin3.0-Mistral-24B-F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use eaddario/Dolphin3.0-Mistral-24B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf eaddario/Dolphin3.0-Mistral-24B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf eaddario/Dolphin3.0-Mistral-24B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf eaddario/Dolphin3.0-Mistral-24B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf eaddario/Dolphin3.0-Mistral-24B-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf eaddario/Dolphin3.0-Mistral-24B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf eaddario/Dolphin3.0-Mistral-24B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf eaddario/Dolphin3.0-Mistral-24B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf eaddario/Dolphin3.0-Mistral-24B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/eaddario/Dolphin3.0-Mistral-24B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use eaddario/Dolphin3.0-Mistral-24B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eaddario/Dolphin3.0-Mistral-24B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eaddario/Dolphin3.0-Mistral-24B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/eaddario/Dolphin3.0-Mistral-24B-GGUF:Q4_K_M

Ollama
How to use eaddario/Dolphin3.0-Mistral-24B-GGUF with Ollama:
```
ollama run hf.co/eaddario/Dolphin3.0-Mistral-24B-GGUF:Q4_K_M
```

Unsloth Studio

How to use eaddario/Dolphin3.0-Mistral-24B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for eaddario/Dolphin3.0-Mistral-24B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for eaddario/Dolphin3.0-Mistral-24B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for eaddario/Dolphin3.0-Mistral-24B-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use eaddario/Dolphin3.0-Mistral-24B-GGUF with Docker Model Runner:
```
docker model run hf.co/eaddario/Dolphin3.0-Mistral-24B-GGUF:Q4_K_M
```

Lemonade

How to use eaddario/Dolphin3.0-Mistral-24B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull eaddario/Dolphin3.0-Mistral-24B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Dolphin3.0-Mistral-24B-GGUF-Q4_K_M

List all available models

lemonade list

eaddario commited on May 7, 2025

Commit

ca0b1af

verified ·

1 Parent(s): 73d4a8f

Regenerate imatrices

Browse files

Files changed (3) hide show

imatrix/imatrix-Dolphin3.0-Mistral-24B-micro.dat +2 -2
imatrix/imatrix-Dolphin3.0-Mistral-24B-small.dat +2 -2
imatrix/imatrix-Dolphin3.0-Mistral-24B-tiny.dat +2 -2

imatrix/imatrix-Dolphin3.0-Mistral-24B-micro.dat CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ad6186b276f24a3920a74349d5c90ef6030b146f4fc64e705e42ed45cb6ee3e
-size 10003550

 version https://git-lfs.github.com/spec/v1
+oid sha256:799c441f23c8bb4e2fdc6fb1966ce820fea35b2456225056720f5aedbe077aad
+size 10024055

imatrix/imatrix-Dolphin3.0-Mistral-24B-small.dat CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c31d5a6edc6054b5fa06b4c0ee9dbda59f034d200faa2ea9cd88357bd3e03d8
-size 10003550

 version https://git-lfs.github.com/spec/v1
+oid sha256:a2a781bc1b13a7da4da9e9651dfa439fe056afd58c2b25b21db5247883c46c6a
+size 10024055

imatrix/imatrix-Dolphin3.0-Mistral-24B-tiny.dat CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c38c99ca4454fa640c298ddc535ceb720483718bc1fb889f2b1a6a284286b1ae
-size 10003549

 version https://git-lfs.github.com/spec/v1
+oid sha256:bdf3b303138893262344d00c1e9a646574d9cc81d6da0e8d9bc7033c2c00455a
+size 10024054