Instructions to use chatpig/llama-3.1-8b-encoder-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use chatpig/llama-3.1-8b-encoder-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 chatpig/llama-3.1-8b-encoder-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf chatpig/llama-3.1-8b-encoder-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 chatpig/llama-3.1-8b-encoder-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf chatpig/llama-3.1-8b-encoder-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 chatpig/llama-3.1-8b-encoder-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf chatpig/llama-3.1-8b-encoder-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 chatpig/llama-3.1-8b-encoder-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf chatpig/llama-3.1-8b-encoder-gguf:Q4_K_M

Use Docker

docker model run hf.co/chatpig/llama-3.1-8b-encoder-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use chatpig/llama-3.1-8b-encoder-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chatpig/llama-3.1-8b-encoder-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": "chatpig/llama-3.1-8b-encoder-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/chatpig/llama-3.1-8b-encoder-gguf:Q4_K_M

Ollama
How to use chatpig/llama-3.1-8b-encoder-gguf with Ollama:
```
ollama run hf.co/chatpig/llama-3.1-8b-encoder-gguf:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use chatpig/llama-3.1-8b-encoder-gguf with Docker Model Runner:
```
docker model run hf.co/chatpig/llama-3.1-8b-encoder-gguf:Q4_K_M
```

Lemonade

How to use chatpig/llama-3.1-8b-encoder-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull chatpig/llama-3.1-8b-encoder-gguf:Q4_K_M

Run and chat with the model

lemonade run user.llama-3.1-8b-encoder-gguf-Q4_K_M

List all available models

lemonade list

Atomic Chat

Nothing Works for HiDream

by qpqpqpqpqpqp - opened Dec 17, 2025

Discussion

qpqpqpqpqpqp

Dec 17, 2025

calcuis' GGUF CLIP Loader:
llama3.1-encoder-q3_k_m.gguf
RuntimeError: Error(s) in loading state_dict for Llama2:
size mismatch for model.embed_tokens.weight: copying a param with shape torch.Size([128320, 4096]) from checkpoint, the shape in current model is torch.Size([128256, 4096]).
I had to download a quant of Llama from someone else

calcuis

Dec 17, 2025

not test that model for very long; guess something changed over the time; have you found the one working for this?

calcuis

Dec 17, 2025

•

edited Dec 17, 2025

oh, i see; they changed to the old scheme for this for some reason
token_embd.weight [4 096, 128 256]

https://huggingface.co/kaetemi/Meta-Llama-3.1-8B-Q4_K_M-GGUF-old/blob/main/meta-llama-3.1-8b-q4_k_m.gguf

and this one should work also:
https://huggingface.co/chatpig/encoder/blob/main/llama-hidream-q2_k.gguf

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment