Instructions to use LiquidAI/LFM2.5-1.2B-Instruct-DSpark-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 LiquidAI/LFM2.5-1.2B-Instruct-DSpark-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 LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf LiquidAI/LFM2.5-1.2B-Instruct-DSpark-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 LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf LiquidAI/LFM2.5-1.2B-Instruct-DSpark-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 LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf LiquidAI/LFM2.5-1.2B-Instruct-DSpark-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 LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF:Q4_K_M

Use Docker

docker model run hf.co/LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LiquidAI/LFM2.5-1.2B-Instruct-DSpark-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": "LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF:Q4_K_M

Ollama
How to use LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF with Ollama:
```
ollama run hf.co/LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF:Q4_K_M
```
Unsloth Desktop

How to use LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LiquidAI/LFM2.5-1.2B-Instruct-DSpark-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": "LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF with Docker Model Runner:
```
docker model run hf.co/LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF:Q4_K_M
```

Lemonade

How to use LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.LFM2.5-1.2B-Instruct-DSpark-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use LiquidAI/LFM2.5-1.2B-Instruct-DSpark-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 LiquidAI/LFM2.5-1.2B-Instruct-DSpark-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 LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use LiquidAI/LFM2.5-1.2B-Instruct-DSpark-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LiquidAI/LFM2.5-1.2B-Instruct-DSpark-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 "LiquidAI/LFM2.5-1.2B-Instruct-DSpark-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"

tugot17

iamleonie commited on 22 days ago

Commit

9235d67

1 Parent(s): 8a7cd88

Rename GGUF files: remove Draft-v1 from filenames (#1)

Browse files

- Rename GGUF files: remove Draft-v1 from filenames (a848f4d49defaf9c3953e968bdd6f9f52a126b3f)

Co-authored-by: Leonie Monigatti <iamleonie@users.noreply.huggingface.co>

Files changed (5) hide show

.gitattributes +3 -0
LFM2.5-1.2B-Instruct-DSpark-Draft-v1-F16.gguf → LFM2.5-1.2B-Instruct-DSpark-F16.gguf +0 -0
LFM2.5-1.2B-Instruct-DSpark-Draft-v1-Q4_K_M.gguf → LFM2.5-1.2B-Instruct-DSpark-Q4_K_M.gguf +0 -0
LFM2.5-1.2B-Instruct-DSpark-Draft-v1-Q8_0.gguf → LFM2.5-1.2B-Instruct-DSpark-Q8_0.gguf +0 -0
README.md +5 -5

.gitattributes CHANGED Viewed

@@ -36,3 +36,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 LFM2.5-1.2B-Instruct-DSpark-Draft-v1-F16.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-1.2B-Instruct-DSpark-Draft-v1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-1.2B-Instruct-DSpark-Draft-v1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

 LFM2.5-1.2B-Instruct-DSpark-Draft-v1-F16.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-1.2B-Instruct-DSpark-Draft-v1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-1.2B-Instruct-DSpark-Draft-v1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LFM2.5-1.2B-Instruct-DSpark-F16.gguf filter=lfs diff=lfs merge=lfs -text
+LFM2.5-1.2B-Instruct-DSpark-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+LFM2.5-1.2B-Instruct-DSpark-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

LFM2.5-1.2B-Instruct-DSpark-Draft-v1-F16.gguf → LFM2.5-1.2B-Instruct-DSpark-F16.gguf RENAMED Viewed

File without changes

LFM2.5-1.2B-Instruct-DSpark-Draft-v1-Q4_K_M.gguf → LFM2.5-1.2B-Instruct-DSpark-Q4_K_M.gguf RENAMED Viewed

File without changes

LFM2.5-1.2B-Instruct-DSpark-Draft-v1-Q8_0.gguf → LFM2.5-1.2B-Instruct-DSpark-Q8_0.gguf RENAMED Viewed

File without changes

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
 library_name: llama.cpp
-base_model: LiquidAI/LFM2.5-1.2B-Instruct-DSpark-Draft-v1
 license: other
 license_name: lfm1.0
 license_link: LICENSE
@@ -39,9 +39,9 @@ Find more information about LFM2.5-DSpark in our [blog post](https://www.liquid.
 | file | quant | size | notes |
 |---|---|---:|---|
-| `LFM2.5-1.2B-Instruct-DSpark-Draft-v1-F16.gguf` | F16 | 594 MB | best accept length, recommended when memory allows |
-| `LFM2.5-1.2B-Instruct-DSpark-Draft-v1-Q8_0.gguf` | Q8_0 | 315 MB | accept length −2% vs F16 |
-| `LFM2.5-1.2B-Instruct-DSpark-Draft-v1-Q4_K_M.gguf` | Q4_K_M | 174 MB | accept length −3% vs F16, smallest recommended — sub-4-bit draft quants measurably hurt both accept length and throughput |
 Draft quantization changes speed only marginally (the drafter is a small share of each cycle); choose by memory budget. The target model quant is the main speed/quality lever and is independent of this file.
@@ -49,7 +49,7 @@ Draft quantization changes speed only marginally (the drafter is a small share o
 ```bash
 llama-server -m LFM2.5-1.2B-Instruct-F16.gguf \
-  -md LFM2.5-1.2B-Instruct-DSpark-Draft-v1-F16.gguf \
   --spec-type draft-dspark --spec-draft-n-max 10 --spec-draft-n-min 0 \
   -fa on -ngl 99
 ```

 ---
 library_name: llama.cpp
+base_model: LiquidAI/LFM2.5-1.2B-Instruct-DSpark
 license: other
 license_name: lfm1.0
 license_link: LICENSE
 | file | quant | size | notes |
 |---|---|---:|---|
+| `LFM2.5-1.2B-Instruct-DSpark-F16.gguf` | F16 | 594 MB | best accept length, recommended when memory allows |
+| `LFM2.5-1.2B-Instruct-DSpark-Q8_0.gguf` | Q8_0 | 315 MB | accept length −2% vs F16 |
+| `LFM2.5-1.2B-Instruct-DSpark-Q4_K_M.gguf` | Q4_K_M | 174 MB | accept length −3% vs F16, smallest recommended — sub-4-bit draft quants measurably hurt both accept length and throughput |
 Draft quantization changes speed only marginally (the drafter is a small share of each cycle); choose by memory budget. The target model quant is the main speed/quality lever and is independent of this file.
 ```bash
 llama-server -m LFM2.5-1.2B-Instruct-F16.gguf \
+  -md LFM2.5-1.2B-Instruct-DSpark-F16.gguf \
   --spec-type draft-dspark --spec-draft-n-max 10 --spec-draft-n-min 0 \
   -fa on -ngl 99
 ```