Instructions to use tensorblock/MiniMerlin-3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/MiniMerlin-3B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/MiniMerlin-3B-GGUF",
	filename="MiniMerlin-3B-Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use tensorblock/MiniMerlin-3B-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/MiniMerlin-3B-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/MiniMerlin-3B-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/MiniMerlin-3B-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/MiniMerlin-3B-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/MiniMerlin-3B-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/MiniMerlin-3B-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/MiniMerlin-3B-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/MiniMerlin-3B-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/MiniMerlin-3B-GGUF:Q2_K

LM Studio
Jan
Ollama
How to use tensorblock/MiniMerlin-3B-GGUF with Ollama:
```
ollama run hf.co/tensorblock/MiniMerlin-3B-GGUF:Q2_K
```

Unsloth Studio new

How to use tensorblock/MiniMerlin-3B-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/MiniMerlin-3B-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/MiniMerlin-3B-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/MiniMerlin-3B-GGUF to start chatting

Docker Model Runner
How to use tensorblock/MiniMerlin-3B-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/MiniMerlin-3B-GGUF:Q2_K
```

Lemonade

How to use tensorblock/MiniMerlin-3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/MiniMerlin-3B-GGUF:Q2_K

Run and chat with the model

lemonade run user.MiniMerlin-3B-GGUF-Q2_K

List all available models

lemonade list

morriszms commited on Jan 27

Commit

e83de16

verified ·

1 Parent(s): e95946f

Remove .gguf files (keep Q2_K.gguf)

Browse files

Files changed (11) hide show

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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:09b46018f9dc39adcb5abdb0effe6e03efe580875de8217e9c5efc7898dba921
-size 1631048704

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d2649fb62ae0324ce826cad1a2a0ae7a908cd46679be8817c9fed2b0dd3d4d73
-size 1504433152

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:349f0e446c5c9e3702dc17b1afbdd1db6986a258dd80494dbb1a3c937d27377c
-size 1358550016

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4fea54d13f2b89d912764341fbe8a9b966e8c1b740d152cb24cdab0f107d2e54
-size 1739602432

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:60b03d7829d8f8f8dd9dae1e631b0a147a70ec5c0b221bece1bab222e66294f1
-size 1846655488