Instructions to use mindi-dev/experience-extractor-350m-v1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mindi-dev/experience-extractor-350m-v1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mindi-dev/experience-extractor-350m-v1-GGUF",
	filename="experience-extractor-350m-v1-Q4_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mindi-dev/experience-extractor-350m-v1-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 mindi-dev/experience-extractor-350m-v1-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf mindi-dev/experience-extractor-350m-v1-GGUF:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mindi-dev/experience-extractor-350m-v1-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf mindi-dev/experience-extractor-350m-v1-GGUF:Q4_0

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 mindi-dev/experience-extractor-350m-v1-GGUF:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf mindi-dev/experience-extractor-350m-v1-GGUF:Q4_0

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 mindi-dev/experience-extractor-350m-v1-GGUF:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mindi-dev/experience-extractor-350m-v1-GGUF:Q4_0

Use Docker

docker model run hf.co/mindi-dev/experience-extractor-350m-v1-GGUF:Q4_0

LM Studio
Jan

vLLM

How to use mindi-dev/experience-extractor-350m-v1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mindi-dev/experience-extractor-350m-v1-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": "mindi-dev/experience-extractor-350m-v1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mindi-dev/experience-extractor-350m-v1-GGUF:Q4_0

Ollama
How to use mindi-dev/experience-extractor-350m-v1-GGUF with Ollama:
```
ollama run hf.co/mindi-dev/experience-extractor-350m-v1-GGUF:Q4_0
```

Unsloth Studio

How to use mindi-dev/experience-extractor-350m-v1-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 mindi-dev/experience-extractor-350m-v1-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 mindi-dev/experience-extractor-350m-v1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mindi-dev/experience-extractor-350m-v1-GGUF to start chatting

How to use mindi-dev/experience-extractor-350m-v1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mindi-dev/experience-extractor-350m-v1-GGUF:Q4_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mindi-dev/experience-extractor-350m-v1-GGUF:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mindi-dev/experience-extractor-350m-v1-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 mindi-dev/experience-extractor-350m-v1-GGUF:Q4_0

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 mindi-dev/experience-extractor-350m-v1-GGUF:Q4_0

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use mindi-dev/experience-extractor-350m-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/mindi-dev/experience-extractor-350m-v1-GGUF:Q4_0
```

Lemonade

How to use mindi-dev/experience-extractor-350m-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mindi-dev/experience-extractor-350m-v1-GGUF:Q4_0

Run and chat with the model

lemonade run user.experience-extractor-350m-v1-GGUF-Q4_0

List all available models

lemonade list

experience-extractor-350m-v1 (GGUF)

A small, on-device structured fact extractor for memory engines, fine-tuned from LiquidAI/LFM2.5-350M (full fine-tune (mlx-lm)). It reads a chat transcript and emits every storable fact as JSON in a fixed 8-field schema:

{"facts": [
  {"what": "...", "when": null, "where": null, "why": null,
   "who": ["..."], "fact_type": "world|experience",
   "entities": ["..."], "message_refs": ["id:m07"]}
]}

It powers the experience memory engine (EXPERIENCE_EXTRACTOR=lfm25). This repo holds the GGUF quantizations for llama.cpp, Ollama, LM Studio, and the crate's lfm25 path (which adds grammar-constrained decoding).

Evaluation (LongMemEval-cleaned "KU", content-recall)

Run it windowed. Whole-transcript extraction caps a small model near 0.62; sliding a 5-message window and unioning the per-window facts is the recall mechanism and the recommended deploy mode. Pairing the 350M + 1.2B as an ensemble reaches ~0.986 on KU.

mode	recall	mean facts/row	repeat
5-msg windowed (recommended)	0.931	29–45	high (use dedup)
5-msg windowed + semantic dedup@0.6	0.889	~15	~0.16 (clean)
whole-transcript (single pass)	0.625	low	low

Files

file	quant	size	sha256	bytes
`experience-extractor-350m-v1-Q4_0.gguf`	Q4_0 (recommended)	209 MB	`ae187a5ab72f60f7…`	219,309,152
`experience-extractor-350m-v1-Q8_0.gguf`	Q8_0 (higher precision)	362 MB	`c3b43f87fd5dc36c…`	379,216,992

Usage

Ollama — ready extractor (this repo ships a Modelfile with the 8-field system prompt baked in):

hf download mindi-dev/experience-extractor-350m-v1-GGUF --include "*Q4_0.gguf" Modelfile --local-dir exp-extractor && cd exp-extractor
ollama create experience-extractor-350m -f Modelfile
ollama run experience-extractor-350m "<paste a rendered transcript>"

Or the raw model (no system prompt): ollama run hf.co/mindi-dev/experience-extractor-350m-v1-GGUF:Q4_0

llama.cpp: llama-cli -hf mindi-dev/experience-extractor-350m-v1-GGUF:Q4_0

experience crate (windowed + constrained 8-field JSON — the validated recall path):

EXPERIENCE_EXTRACTOR=lfm25 EXPERIENCE_EXTRACTOR_MODEL_PATH=./experience-extractor-350m-v1-Q4_0.gguf \
EXPERIENCE_EXTRACTION_WINDOW=5 experience serve

Other formats

MLX 4-bit (Apple Silicon): mindi-dev/experience-extractor-350m-v1-mlx-4bit

Training

Full pipeline at mindi-dev/experience (training/). Fine-tuned on real-distribution LongMemEval transcripts (leakage-safe; held-out KU never trained on) with grounded teacher-generated labels.

License

Fine-tune of LiquidAI/LFM2.5-350M under the LFM Open License v1.0. Redistribution permitted with attribution + change notice; commercial use by entities with ≥ US$10M revenue requires a Liquid AI commercial license (Sec. 5). The crate code is MIT and separate. See NOTICE.md and the full LICENSE in this repo.

Downloads last month: 161

GGUF

Model size

0.4B params

Architecture

lfm2

Hardware compatibility

4-bit

8-bit

Model tree for mindi-dev/experience-extractor-350m-v1-GGUF

Base model

LiquidAI/LFM2.5-350M-Base

Finetuned

LiquidAI/LFM2.5-350M

Quantized

(38)

this model