Instructions to use tensorblock/MetaModelv3-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/MetaModelv3-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/MetaModelv3-GGUF",
	filename="MetaModelv3-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use tensorblock/MetaModelv3-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/MetaModelv3-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/MetaModelv3-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/MetaModelv3-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/MetaModelv3-GGUF:Q2_K

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 tensorblock/MetaModelv3-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/MetaModelv3-GGUF:Q2_K

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 tensorblock/MetaModelv3-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/MetaModelv3-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/MetaModelv3-GGUF:Q2_K

LM Studio
Jan
Ollama
How to use tensorblock/MetaModelv3-GGUF with Ollama:
```
ollama run hf.co/tensorblock/MetaModelv3-GGUF:Q2_K
```

Unsloth Studio new

How to use tensorblock/MetaModelv3-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 tensorblock/MetaModelv3-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 tensorblock/MetaModelv3-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tensorblock/MetaModelv3-GGUF to start chatting

Docker Model Runner
How to use tensorblock/MetaModelv3-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/MetaModelv3-GGUF:Q2_K
```

Lemonade

How to use tensorblock/MetaModelv3-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/MetaModelv3-GGUF:Q2_K

Run and chat with the model

lemonade run user.MetaModelv3-GGUF-Q2_K

List all available models

lemonade list

morriszms commited on Jan 27

Commit

c164b9a

verified ·

1 Parent(s): df69785

Remove .gguf files (keep Q2_K.gguf)

Browse files

Files changed (11) hide show

MetaModelv3-Q3_K_L.gguf +0 -3
MetaModelv3-Q3_K_M.gguf +0 -3
MetaModelv3-Q3_K_S.gguf +0 -3
MetaModelv3-Q4_0.gguf +0 -3
MetaModelv3-Q4_K_M.gguf +0 -3
MetaModelv3-Q4_K_S.gguf +0 -3
MetaModelv3-Q5_0.gguf +0 -3
MetaModelv3-Q5_K_M.gguf +0 -3
MetaModelv3-Q5_K_S.gguf +0 -3
MetaModelv3-Q6_K.gguf +0 -3
MetaModelv3-Q8_0.gguf +0 -3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f14c81851b793a5a81a2602791c012117f00ad3af2df8aa1768b58356215697b
-size 5650750464

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5c1b5d3d0661f6362499e1dd1260b69fa2c4849c314aaf8d6211b957e04675e3
-size 5195668480

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0d9d5ada9850230c9cce075ee7744644d8fb31d72bbffc4013060d7201d553ef
-size 4664564736

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fdac0f1ba2302c0ba4a02c3dc6e2e18ba7564817b648477ceafcb03cf6b68c88
-size 6072384512

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:59cf8362cb7525c833acb87c3ab098871c8a15a1d1dd90fb79c69ee97fa9d298
-size 6461668352