Instructions to use agney/lfm2-herdr-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 agney/lfm2-herdr-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 agney/lfm2-herdr-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf agney/lfm2-herdr-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 agney/lfm2-herdr-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf agney/lfm2-herdr-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 agney/lfm2-herdr-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf agney/lfm2-herdr-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 agney/lfm2-herdr-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf agney/lfm2-herdr-gguf:Q4_K_M

Use Docker

docker model run hf.co/agney/lfm2-herdr-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use agney/lfm2-herdr-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "agney/lfm2-herdr-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": "agney/lfm2-herdr-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/agney/lfm2-herdr-gguf:Q4_K_M

Ollama
How to use agney/lfm2-herdr-gguf with Ollama:
```
ollama run hf.co/agney/lfm2-herdr-gguf:Q4_K_M
```
Unsloth Desktop

How to use agney/lfm2-herdr-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf agney/lfm2-herdr-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": "agney/lfm2-herdr-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use agney/lfm2-herdr-gguf with Docker Model Runner:
```
docker model run hf.co/agney/lfm2-herdr-gguf:Q4_K_M
```

Lemonade

How to use agney/lfm2-herdr-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull agney/lfm2-herdr-gguf:Q4_K_M

Run and chat with the model

lemonade run user.lfm2-herdr-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use agney/lfm2-herdr-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 agney/lfm2-herdr-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 agney/lfm2-herdr-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use agney/lfm2-herdr-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf agney/lfm2-herdr-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 "agney/lfm2-herdr-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"

Herdr expert — LFM2-350M (GGUF)

A merged LoRA fine-tune of LiquidAI/LFM2-350M, trained by the herdr-liquid-finetune repo to be an expert on the Herdr terminal multiplexer (25 Herdr tool-calling ops, plus off-topic refusal). Exported to GGUF for llama.cpp so it runs as a single binary — no Python needed.

The adapter lives at agney/lfm2-herdr-lora; this repo is the same weights merged into the base and quantized.

Files

file	size	exact-call	note
`lfm2-herdr-f16.gguf`	679 MB	96.1%	full-precision baseline
`lfm2-herdr-Q8_0.gguf`	362 MB	96.1%	lossless vs bf16 — best pick
`lfm2-herdr-Q5_K_M.gguf`	249 MB	95.1%	good default (1 pt off)
`lfm2-herdr-Q4_K_M.gguf`	219 MB	92.2%	smallest / most CPU-friendly

Run (llama.cpp)

# 1. build llama.cpp (once): cmake -B build -G Ninja && cmake --build build
./build/bin/llama-cli \
  -m lfm2-herdr-Q4_K_M.gguf \
  -p "$(cat prompt.txt)" \
  -st -n 128 --temp 0

prompt.txt is the same system env + Herdr tool schemas the training prompt used — build it with the fine-tune repo's tokenizer.apply_chat_template(tools=...) (or copy the 25 herdr_tools.SCHEMAS into the prompt). The model answers in the native <|tool_call_start|>[name(k=v, ...)]<|tool_call_end|> syntax; parse it with the repo's eval_lfm2.parse_calls.

For an OpenAI-style HTTP endpoint use llama-server with the same model, and send your chat request with tools=.

Measured accuracy (pinned 120-row holdout, v8)

Scored with scripts/eval_gguf.py (same prompt + parse_calls as the eval_lfm2.py transformers eval). All quantizations keep 100% off-topic; the diff is exact-call and a couple of arg-grounding rows.

file	size	exact-call	tool-sel	off-topic
bf16 adapter (transformers)	—	96.1%	97.1%	100%
`lfm2-herdr-f16.gguf`	679 MB	96.1%	97.1%	100%
`lfm2-herdr-Q8_0.gguf`	362 MB	96.1%	97.1%	100%
`lfm2-herdr-Q5_K_M.gguf`	249 MB	95.1%	97.1%	100%
`lfm2-herdr-Q4_K_M.gguf`	219 MB	92.2%	98.1%	100%

Lossless: F16 and Q8_0 reproduce the bf16 adapter exactly; the merge + GGUF conversion introduces no behavior change. Q4_K_M costs ~4 pts (mostly the pane_current / pane_split arg-grounding rows the bf16 model already struggles with). Pick Q8_0 for accuracy, Q5_K_M for the best size/accuracy balance, Q4_K_M only if size is the priority.

Notes

Narrow specialist: plans the 25 Herdr ops and refuses off-topic prompts; does not do general chat, code, or reasoning.
GGUF is a storage format — you still need the llama.cpp binaries to run it, and you still format the prompt/tool list yourself. It removes the Python model-loading layer, not the inference harness.
License: MIT (project weights). The base model remains under its own license.

Downloads last month: -

GGUF

Model size

0.4B params

Architecture

lfm2

Hardware compatibility

4-bit

5-bit

8-bit

16-bit

Model tree for agney/lfm2-herdr-gguf

Base model

LiquidAI/LFM2-350M

Quantized

(43)

this model