Instructions to use tensorblock/Llammas-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/Llammas-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="tensorblock/Llammas-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tensorblock/Llammas-GGUF", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tensorblock/Llammas-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/Llammas-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": "tensorblock/Llammas-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tensorblock/Llammas-GGUF

SGLang

How to use tensorblock/Llammas-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "tensorblock/Llammas-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/Llammas-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "tensorblock/Llammas-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/Llammas-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tensorblock/Llammas-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/Llammas-GGUF
```

tartuNLP/Llammas - GGUF

This repo contains GGUF format model files for tartuNLP/Llammas.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Our projects

Forge

An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio

A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

## Prompt template

<|system|>
{system_prompt}
<|user|>
{prompt}
<|assistant|>

Model file specification

Filename	Quant type	File Size	Description
Llammas-Q2_K.gguf	Q2_K	2.533 GB	smallest, significant quality loss - not recommended for most purposes
Llammas-Q3_K_S.gguf	Q3_K_S	2.948 GB	very small, high quality loss
Llammas-Q3_K_M.gguf	Q3_K_M	3.298 GB	very small, high quality loss
Llammas-Q3_K_L.gguf	Q3_K_L	3.597 GB	small, substantial quality loss
Llammas-Q4_0.gguf	Q4_0	3.826 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Llammas-Q4_K_S.gguf	Q4_K_S	3.857 GB	small, greater quality loss
Llammas-Q4_K_M.gguf	Q4_K_M	4.081 GB	medium, balanced quality - recommended
Llammas-Q5_0.gguf	Q5_0	4.652 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Llammas-Q5_K_S.gguf	Q5_K_S	4.652 GB	large, low quality loss - recommended
Llammas-Q5_K_M.gguf	Q5_K_M	4.783 GB	large, very low quality loss - recommended
Llammas-Q6_K.gguf	Q6_K	5.529 GB	very large, extremely low quality loss
Llammas-Q8_0.gguf	Q8_0	7.161 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/Llammas-GGUF --include "Llammas-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/Llammas-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'

Downloads last month: 28

GGUF

Hardware compatibility

2-bit

Model tree for tensorblock/Llammas-GGUF

Base model

meta-llama/Llama-2-7b-hf

Finetuned

tartuNLP/Llammas-base

Finetuned

tartuNLP/Llammas

Quantized

(4)

this model