Instructions to use Raydev/LLaMA3.2-3B-Instruct-talkie-distill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Raydev/LLaMA3.2-3B-Instruct-talkie-distill 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 Raydev/LLaMA3.2-3B-Instruct-talkie-distill:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Raydev/LLaMA3.2-3B-Instruct-talkie-distill:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Raydev/LLaMA3.2-3B-Instruct-talkie-distill:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Raydev/LLaMA3.2-3B-Instruct-talkie-distill: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 Raydev/LLaMA3.2-3B-Instruct-talkie-distill:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Raydev/LLaMA3.2-3B-Instruct-talkie-distill: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 Raydev/LLaMA3.2-3B-Instruct-talkie-distill:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Raydev/LLaMA3.2-3B-Instruct-talkie-distill:Q4_K_M

Use Docker

docker model run hf.co/Raydev/LLaMA3.2-3B-Instruct-talkie-distill:Q4_K_M

LM Studio
Jan
Ollama
How to use Raydev/LLaMA3.2-3B-Instruct-talkie-distill with Ollama:
```
ollama run hf.co/Raydev/LLaMA3.2-3B-Instruct-talkie-distill:Q4_K_M
```

Unsloth Studio

How to use Raydev/LLaMA3.2-3B-Instruct-talkie-distill 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 Raydev/LLaMA3.2-3B-Instruct-talkie-distill 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 Raydev/LLaMA3.2-3B-Instruct-talkie-distill to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Raydev/LLaMA3.2-3B-Instruct-talkie-distill to start chatting

How to use Raydev/LLaMA3.2-3B-Instruct-talkie-distill with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Raydev/LLaMA3.2-3B-Instruct-talkie-distill:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Raydev/LLaMA3.2-3B-Instruct-talkie-distill:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use Raydev/LLaMA3.2-3B-Instruct-talkie-distill with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Raydev/LLaMA3.2-3B-Instruct-talkie-distill:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Raydev/LLaMA3.2-3B-Instruct-talkie-distill:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use Raydev/LLaMA3.2-3B-Instruct-talkie-distill with Docker Model Runner:
```
docker model run hf.co/Raydev/LLaMA3.2-3B-Instruct-talkie-distill:Q4_K_M
```

Lemonade

How to use Raydev/LLaMA3.2-3B-Instruct-talkie-distill with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Raydev/LLaMA3.2-3B-Instruct-talkie-distill:Q4_K_M

Run and chat with the model

lemonade run user.LLaMA3.2-3B-Instruct-talkie-distill-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Raydev/LLaMA3.2-3B-Instruct-talkie-distill with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Raydev/LLaMA3.2-3B-Instruct-talkie-distill:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Raydev/LLaMA3.2-3B-Instruct-talkie-distill:Q4_K_M

Run Hermes

hermes

Atomic Chat

LLaMA3.2-3B-Instruct-talkie-distill / README.md

Raydev

Update README.md

e9861b2 verified about 19 hours ago

preview code

Raw

History Blame Contribute Delete

3.51 kB

	---
	license: llama3.2
	datasets:
	- Raydev/Talkie1930-1M
	language:
	- en
	base_model:
	- unsloth/Llama-3.2-3B-Instruct
	tags:
	- distillation
	- talkie
	- vintage
	- LLaMA3.2-talkie
	- LoRA
	---

	# LLaMA-3.2-3B-it-talkie

	This repository has a distilled version of LLaMA-3.2-3B, trained on [my 1M token sized Talkie dataset](https://huggingface.co/datasets/Raydev/Talkie1930-1M) for two epochs. Just as with my [last talkie-distill release](https://huggingface.co/Raydev/Qwen3.5-0.8B-Talkie-Distill) the [safetensor](https://huggingface.co/Raydev/LLaMA-3.2-3B-Instruct-talkie-distill-safetensors/) version of this model will be available as well and the configuration i used as well as more.

	The reason for the upscale from the last, Qwen3.5-0.8B model to this one is to see if a larger model handles it better, and it actually seems to. It's able to generalize it's new training data and way of speaking with moden concepts, even if it does get things more inaccurately (due to it's training data).

	*NOTE: This is a 'LoRA' finetune.

	Here is some examples of that generalization:

	```txt
	INPUT: What is a large language model?

	OUTPUT: A large language model is a statistical model for representing
	a language by a set of statistical associations between
	characters. The model is built on the assumption that
	each character can be defined as a probability distribution
	over a large number of characters, and that the distribu-
	tions for different characters are independent and identi-
	cal. The model must, therefore, be a large, one, and
	can be regarded as an aggregate of many smaller models,
	each corresponding to one of the characters of the language.
	The model must be built up gradually, step by step, by
	proceeding from the simplest to the most complex, so that
	at each stage the total number of characters shall be
	increased by a small increment.


	INPUT: What is tokenization and back propagation?

	OUTPUT: Tokenization and back propagation are the processes by
	which the model is fitted to the language data in hand.
	Tokenization means the separation of the language into
	characters, and back propagation means the process by
	which the statistical weights are modified so as to minimise
	the difference between the model and the language data.
	The process of fitting the model to the language data
	consists in adjusting the statistical weights in such a way
	that the output of the model shall be most like the actual
	language data. The differences between the model and the
	data are calculated in terms of some measure of disti-
	bution (e.g. the sum of squares of errors of prediction),
	and these are made minimum by an iterative procedure
	in which the model is gradually changed, and the
	difference is recalculated, until no further improvement
	is perceptible.
	```

	It does confuse our modern knowledge of what LLMs, Tokenization, and backprop are (this is to be expected with this distillation.), but it does manage to essentially merge it's knowledge with the style it was trained on.

	Since this model is LLaMA you are beholden to the LLaMA-3.2 Community License Agreement, It is not my choice. I will soon release a alternative Qwen3.5-4B distillation for those who want a more liberating license. As always, Credit is given to [the talkie team](https://talkie-lm.com/introducing-talkie) for creating Talkie, and releasing it to the public. The [dataset](https://huggingface.co/datasets/Raydev/Talkie1930-1M) this model was trained on is publicly available, if you want to run your own distillation.