Instructions to use hekod19045/llama-cuda with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hekod19045/llama-cuda with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="hekod19045/llama-cuda",
	filename="models/ggml-vocab-aquila.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use hekod19045/llama-cuda with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf hekod19045/llama-cuda
# Run inference directly in the terminal:
llama-cli -hf hekod19045/llama-cuda

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf hekod19045/llama-cuda
# Run inference directly in the terminal:
llama-cli -hf hekod19045/llama-cuda

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 hekod19045/llama-cuda
# Run inference directly in the terminal:
./llama-cli -hf hekod19045/llama-cuda

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 hekod19045/llama-cuda
# Run inference directly in the terminal:
./build/bin/llama-cli -hf hekod19045/llama-cuda

Use Docker

docker model run hf.co/hekod19045/llama-cuda

LM Studio
Jan
Ollama
How to use hekod19045/llama-cuda with Ollama:
```
ollama run hf.co/hekod19045/llama-cuda
```

Unsloth Studio

How to use hekod19045/llama-cuda 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 hekod19045/llama-cuda 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 hekod19045/llama-cuda to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for hekod19045/llama-cuda to start chatting

Docker Model Runner
How to use hekod19045/llama-cuda with Docker Model Runner:
```
docker model run hf.co/hekod19045/llama-cuda
```

Lemonade

How to use hekod19045/llama-cuda with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull hekod19045/llama-cuda

Run and chat with the model

lemonade run user.llama-cuda-{{QUANT_TAG}}

List all available models

lemonade list

llama-cuda / docs /multimodal.md

hekod19045

Upload folder using huggingface_hub

8eea90d verified about 1 year ago

preview code

raw

history blame contribute delete

2.86 kB

Multimodal

llama.cpp supports multimodal input via libmtmd. Currently, there are 2 tools support this feature:

llama-mtmd-cli
llama-server via OpenAI-compatible /chat/completions API

To enable it, can use use one of the 2 methods below:

Use -hf option with a supported model (see a list of pre-quantized model below)
- To load a model using -hf while disabling multimodal, use --no-mmproj
- To load a model using -hf while using a custom mmproj file, use --mmproj local_file.gguf
Use -m model.gguf option with --mmproj file.gguf to specify text and multimodal projector respectively

By default, multimodal projector will be offloaded to GPU. To disable this, add --no-mmproj-offload

For example:

# simple usage with CLI
llama-mtmd-cli -hf ggml-org/gemma-3-4b-it-GGUF

# simple usage with server
llama-server -hf ggml-org/gemma-3-4b-it-GGUF

# using local file
llama-server -m gemma-3-4b-it-Q4_K_M.gguf --mmproj mmproj-gemma-3-4b-it-Q4_K_M.gguf

# no GPU offload
llama-server -hf ggml-org/gemma-3-4b-it-GGUF --no-mmproj-offload

Pre-quantized models

These are ready-to-use models, most of them come with Q4_K_M quantization by default. They can be found at the Hugging Face page of the ggml-org: https://huggingface.co/ggml-org

Replaces the (tool_name) with the name of binary you want to use. For example, llama-mtmd-cli or llama-server

NOTE: some models may require large context window, for example: -c 8192

# Gemma 3
(tool_name) -hf ggml-org/gemma-3-4b-it-GGUF
(tool_name) -hf ggml-org/gemma-3-12b-it-GGUF
(tool_name) -hf ggml-org/gemma-3-27b-it-GGUF

# SmolVLM
(tool_name) -hf ggml-org/SmolVLM-Instruct-GGUF
(tool_name) -hf ggml-org/SmolVLM-256M-Instruct-GGUF
(tool_name) -hf ggml-org/SmolVLM-500M-Instruct-GGUF
(tool_name) -hf ggml-org/SmolVLM2-2.2B-Instruct-GGUF
(tool_name) -hf ggml-org/SmolVLM2-256M-Video-Instruct-GGUF
(tool_name) -hf ggml-org/SmolVLM2-500M-Video-Instruct-GGUF

# Pixtral 12B
(tool_name) -hf ggml-org/pixtral-12b-GGUF

# Qwen 2 VL
(tool_name) -hf ggml-org/Qwen2-VL-2B-Instruct-GGUF
(tool_name) -hf ggml-org/Qwen2-VL-7B-Instruct-GGUF

# Qwen 2.5 VL
(tool_name) -hf ggml-org/Qwen2.5-VL-3B-Instruct-GGUF
(tool_name) -hf ggml-org/Qwen2.5-VL-7B-Instruct-GGUF
(tool_name) -hf ggml-org/Qwen2.5-VL-32B-Instruct-GGUF
(tool_name) -hf ggml-org/Qwen2.5-VL-72B-Instruct-GGUF

# Mistral Small 3.1 24B (IQ2_M quantization)
(tool_name) -hf ggml-org/Mistral-Small-3.1-24B-Instruct-2503-GGUF

# InternVL 2.5 and 3
(tool_name) -hf ggml-org/InternVL2_5-1B-GGUF
(tool_name) -hf ggml-org/InternVL2_5-4B-GGUF
(tool_name) -hf ggml-org/InternVL3-1B-Instruct-GGUF
(tool_name) -hf ggml-org/InternVL3-2B-Instruct-GGUF
(tool_name) -hf ggml-org/InternVL3-8B-Instruct-GGUF
(tool_name) -hf ggml-org/InternVL3-14B-Instruct-GGUF