Instructions to use lmstudio-community/flint-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 lmstudio-community/flint-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 lmstudio-community/flint-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lmstudio-community/flint-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 lmstudio-community/flint-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lmstudio-community/flint-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 lmstudio-community/flint-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf lmstudio-community/flint-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 lmstudio-community/flint-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lmstudio-community/flint-GGUF:Q4_K_M

Use Docker

docker model run hf.co/lmstudio-community/flint-GGUF:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use lmstudio-community/flint-GGUF with Ollama:
```
ollama run hf.co/lmstudio-community/flint-GGUF:Q4_K_M
```
Unsloth Desktop

How to use lmstudio-community/flint-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lmstudio-community/flint-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "lmstudio-community/flint-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use lmstudio-community/flint-GGUF with Docker Model Runner:
```
docker model run hf.co/lmstudio-community/flint-GGUF:Q4_K_M
```

Lemonade

How to use lmstudio-community/flint-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lmstudio-community/flint-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.flint-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use lmstudio-community/flint-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lmstudio-community/flint-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default lmstudio-community/flint-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use lmstudio-community/flint-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lmstudio-community/flint-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "lmstudio-community/flint-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Chat Template fix.

by redwolfjmt - opened about 13 hours ago

Discussion

redwolfjmt

about 13 hours ago

Disclosure: This is an issue with the original chat template from RecursiveSI which seems to have been carried forward by most forks of the model.

LM Studio 0.4.26 (build 4),
CUDA12 llama.cpp (LM Studio Runtime) v2.65.0
Harmony (win) v0.3.6

This error appears in the chat template:
Failed to parse Jinja template: Unexpected escaped character: x

It has to do with this line:

| replace("\x00", "")

Apparently the reason is that \x is not a recognized command in lm studio, so you'd need to change this.
There are two solutions that I've tried that seem to work

You either remove the line all together, or you can add a literal Null Character.

Old Snippet:

{{- t | replace("\x00", "") | replace("", "") | replace("", "")

Option 1:
{{- t | replace("", "") | replace("", "")

Option 2:
{{- t | replace("�", "") | replace("", "") | replace("", "")

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