Instructions to use lewisdog/lfm2.5-350m-cogs-ask-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 lewisdog/lfm2.5-350m-cogs-ask-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 lewisdog/lfm2.5-350m-cogs-ask-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lewisdog/lfm2.5-350m-cogs-ask-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 lewisdog/lfm2.5-350m-cogs-ask-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lewisdog/lfm2.5-350m-cogs-ask-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 lewisdog/lfm2.5-350m-cogs-ask-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf lewisdog/lfm2.5-350m-cogs-ask-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 lewisdog/lfm2.5-350m-cogs-ask-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lewisdog/lfm2.5-350m-cogs-ask-GGUF:Q4_K_M

Use Docker

docker model run hf.co/lewisdog/lfm2.5-350m-cogs-ask-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use lewisdog/lfm2.5-350m-cogs-ask-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lewisdog/lfm2.5-350m-cogs-ask-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": "lewisdog/lfm2.5-350m-cogs-ask-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lewisdog/lfm2.5-350m-cogs-ask-GGUF:Q4_K_M

Ollama
How to use lewisdog/lfm2.5-350m-cogs-ask-GGUF with Ollama:
```
ollama run hf.co/lewisdog/lfm2.5-350m-cogs-ask-GGUF:Q4_K_M
```
Unsloth Desktop

How to use lewisdog/lfm2.5-350m-cogs-ask-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lewisdog/lfm2.5-350m-cogs-ask-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": "lewisdog/lfm2.5-350m-cogs-ask-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use lewisdog/lfm2.5-350m-cogs-ask-GGUF with Docker Model Runner:
```
docker model run hf.co/lewisdog/lfm2.5-350m-cogs-ask-GGUF:Q4_K_M
```

Lemonade

How to use lewisdog/lfm2.5-350m-cogs-ask-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lewisdog/lfm2.5-350m-cogs-ask-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.lfm2.5-350m-cogs-ask-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use lewisdog/lfm2.5-350m-cogs-ask-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 lewisdog/lfm2.5-350m-cogs-ask-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 lewisdog/lfm2.5-350m-cogs-ask-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use lewisdog/lfm2.5-350m-cogs-ask-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lewisdog/lfm2.5-350m-cogs-ask-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 "lewisdog/lfm2.5-350m-cogs-ask-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"

lfm2.5-350m-cogs-ask

A 350M ask student for Cogitarium retrieval-QA. Two tasks:

decompose: split a question into 1-4 retrieval sub-questions → {"subquestions":[...]}
synth: answer strictly from provided wiki notes with inline [note-id] citations → {"answer","citations","abstained"}

Trained on the real cogs serialization — slash note-ids (concepts/planner) and [[wikilinks]] in note bodies — plus frontier-teacher-distilled grounded Q&A generated over the real vault. Correct on the deployment distribution; needs no serving hacks.

Serving pins

temperature 0, repeat_penalty 1.0.
Emits exact slash note-ids and handles [[wikilinks]] in bodies natively — you do NOT need to strip wikilinks or fuzzy-match citations (both were required by the earlier hyphen-id variant). Feed evidence as `### [note-id] Title` exactly as `cogs ask` builds it.
Gate abstention upstream. The abstained flag is only moderately reliable; decide "is this answerable?" from retrieval score / the decompose step and don't depend on the field.

Eval (real vault serialization; grounded citation validity)

Distilled from ~600 frontier-teacher-generated grounded Q&A over the real vault (plus the re-serialized base set). Grounded-citation validity:

set	decompose	grounded exact	grounded lenient	abstain
deployment vault (aoa, notes seen in training)	100%	89%	89%	6/11
out-of-domain (unseen clusters)	100%	58%	65%	3/5

Progression as teacher data scaled (out-of-domain grounded strict): vault-aligned only 38% → +204 teacher 50% → +570 teacher 58%. On the vault it is actually trained over, grounded citation is ~89%. Data quality/quantity — not model size — was the binding constraint. Feed evidence as `### [note-id] Title

; citations come back as exact slash-ids, no serving hacks. Gate abstention upstream (the abstained` flag is only moderately reliable). A strong fast tier; the Qwen3-1.7B student remains the quality tier.

Recommended quant: Q8_0 (379 MB, 509 tok/s on GB10). decompose is flawless at any quant incl. Q4_K_M (229 MB).

This repo

GGUF quant ladder for llama.cpp (F16 / Q8_0 / Q4_K_M). See the quant table above for the recommended pick and per-quant behavior. Run with --temp 0 and the serving pins noted above.

Base model & license

Fine-tuned from LiquidAI/LFM2.5-350M. Use is governed by the LFM Open License v1.0 (lfm1.0) — see the LICENSE in the base repo. This derivative complies with and inherits those terms; attribution to LiquidAI is retained above.

Provenance

LoRA SFT (TRL) on the Cogitarium distillation datasets, DGX Spark (GB10). Full methodology, loss curves, eval harnesses and per-quant results: see the project RESULTS.md. This is the "fast/small tier" of the Cogitarium model picker; the Qwen3-1.7B students remain the quality tier.

Downloads last month: 92

GGUF

Model size

0.4B params

Architecture

lfm2

Hardware compatibility

4-bit

8-bit

16-bit

Model tree for lewisdog/lfm2.5-350m-cogs-ask-GGUF

Base model

LiquidAI/LFM2.5-350M-Base

Finetuned

LiquidAI/LFM2.5-350M

Quantized

(67)

this model