Instructions to use petr567/LFM2.5-2.6B-Windows-RTX-CUDA-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 petr567/LFM2.5-2.6B-Windows-RTX-CUDA-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 petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf petr567/LFM2.5-2.6B-Windows-RTX-CUDA-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 petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf petr567/LFM2.5-2.6B-Windows-RTX-CUDA-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 petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf petr567/LFM2.5-2.6B-Windows-RTX-CUDA-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 petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF:Q4_K_M

Use Docker

docker model run hf.co/petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "petr567/LFM2.5-2.6B-Windows-RTX-CUDA-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": "petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF:Q4_K_M

Ollama
How to use petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF with Ollama:
```
ollama run hf.co/petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF:Q4_K_M
```
Unsloth Desktop

How to use petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf petr567/LFM2.5-2.6B-Windows-RTX-CUDA-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": "petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF with Docker Model Runner:
```
docker model run hf.co/petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF:Q4_K_M
```

Lemonade

How to use petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.LFM2.5-2.6B-Windows-RTX-CUDA-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use petr567/LFM2.5-2.6B-Windows-RTX-CUDA-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 petr567/LFM2.5-2.6B-Windows-RTX-CUDA-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 petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf petr567/LFM2.5-2.6B-Windows-RTX-CUDA-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 "petr567/LFM2.5-2.6B-Windows-RTX-CUDA-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"

LFM2.5-2.6B Q4_K_M Fast — Windows CUDA

This repository contains a directly runnable Q4_K_M GGUF of LiquidAI/LFM2.5-2.6B-GGUF and a validated Fast single-request Windows/CUDA profile for llama.cpp.

The model weights are not modified. The same verified GGUF is published in both paired repositories; only the tested runtime profile differs.

Fast profile: inference is accelerated relative to the same Q4_K_M baseline without the Fast runtime settings. The frozen validation gate detected no quality regression and no new failures. This is a measured result for the documented hardware, workloads, and single-request setup—not a universal guarantee for every prompt or runtime.

Measured Fast result

Primary metric: wall-clock decoded tokens per second for one request, without batching. The profile validation used three workloads with five repetitions each (15 runs total, 256 generated tokens per run).

Workload	Baseline, tok/s	Fast, tok/s	Fast vs baseline
Code copy	114.74	226.27	1.972× (+97.2%)
Editorial rewrite	112.09	141.26	1.260× (+26.0%)
Technical summary	113.30	133.67	1.180× (+18.0%)
All 15 runs, mean ± SD	113.38 ± 1.56	167.07 ± 43.51	1.474× (+47.4%)

Independent quality gate	Baseline	Fast	Regression
Passed tasks	10/12	10/12	None measured

The larger Fast standard deviation reflects the deliberately mixed workload set: repetitive code benefits more than free-form editing and summarization. These are profile-validation measurements, not the pending frozen cross-machine benchmark.

Choose the matching profile

Platform	Hardware/backend	Repository
Windows 11	NVIDIA RTX / CUDA	This repository
Ubuntu	AMD Strix Halo / Vulkan	LFM2.5-2.6B-Ubuntu-Strix-Halo-Vulkan-GGUF

Included weight

File	Quantization	Size	SHA-256
`LFM2.5-2.6B-Q4_K_M.gguf`	Q4_K_M	1,674,454,848 bytes (1.56 GiB)	`79fdf00351b46cf26f020aead28d01889886be87c55fa0eb907e6f9b00bfee14`

Source revision: b22e29ebf6249a8c9fcdda36914743e9980595c4.

Tested setup

Windows 11 laptop
NVIDIA GeForce RTX 4060 Laptop GPU, 8 GiB VRAM
Intel Core i7-13650HX, 64 GiB RAM
NVIDIA driver 591.74
official llama.cpp CUDA server container, build 10066 (86a9c79f8)
context 8,192, one parallel slot, continuous batching disabled

Download and verify

Install the Hugging Face CLI once, or download the GGUF with the file link above.

py -m pip install -U huggingface_hub

$ModelDir = "C:\Models\LFM2.5-2.6B"
New-Item -ItemType Directory -Force -Path $ModelDir | Out-Null

hf download petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF `
  LFM2.5-2.6B-Q4_K_M.gguf `
  --local-dir $ModelDir

$Expected = "79fdf00351b46cf26f020aead28d01889886be87c55fa0eb907e6f9b00bfee14"
$Actual = (Get-FileHash "$ModelDir\LFM2.5-2.6B-Q4_K_M.gguf" -Algorithm SHA256).Hash.ToLower()
if ($Actual -ne $Expected) { throw "GGUF SHA-256 mismatch" }

Run the validated Fast Windows/CUDA profile

Docker Desktop must be configured for NVIDIA GPU access.

$ModelDir = "C:\Models\LFM2.5-2.6B"

docker run --rm --gpus all `
  -p 127.0.0.1:8080:8080 `
  -v "${ModelDir}:/models:ro" `
  --entrypoint /app/llama-server `
  ghcr.io/ggml-org/llama.cpp@sha256:1b3d1458ccda7287feab41b8001311acc03e24cde99ec0a2908fe83830562f38 `
  -m /models/LFM2.5-2.6B-Q4_K_M.gguf `
  --alias lfm2.5-2.6b-q4_k_m `
  --host 0.0.0.0 --port 8080 `
  -c 8192 -np 1 -ngl 99 `
  -t 14 -tb 14 -b 2048 -ub 512 `
  -fa auto -ctk q8_0 -ctv q8_0 `
  --no-cont-batching --no-cache-prompt --cache-ram 0 `
  --slot-prompt-similarity 0 --jinja --no-webui `
  --spec-type ngram-simple `
  --spec-ngram-simple-size-n 8 `
  --spec-ngram-simple-size-m 64 `
  --spec-ngram-simple-min-hits 1 `
  --spec-draft-n-max 64

The OpenAI-compatible endpoint is available at http://127.0.0.1:8080/v1.

$Body = @{
  model = "lfm2.5-2.6b-q4_k_m"
  messages = @(@{ role = "user"; content = "Write a short hello-world function in Python." })
  max_tokens = 128
  temperature = 0.2
} | ConvertTo-Json -Depth 5

Invoke-RestMethod -Method Post `
  -Uri "http://127.0.0.1:8080/v1/chat/completions" `
  -ContentType "application/json" `
  -Body $Body

LM Studio

The GGUF itself can also be opened in LM Studio. Use an 8,192-token context, maximum GPU offload, and one parallel request. The exact ngram-simple profile above requires a compatible llama.cpp server build; do not assume an arbitrary GUI runtime exposes the same acceleration controls.

Release scope

This release contains the runnable weight and the final launch recipe. The frozen cross-machine benchmark package and its results will be attached in a later revision after verification.

Attribution and license

Base model and GGUF: Liquid AI
Upstream repository: LiquidAI/LFM2.5-2.6B-GGUF
License: LFM Open License v1.0; a copy is included as LICENSE

The license includes a commercial-use revenue threshold. Review the included license before use or redistribution.

Downloads last month: 96

GGUF

Model size

3B params

Architecture

lfm2

Hardware compatibility

4-bit

Model tree for petr567/LFM2.5-2.6B-Windows-RTX-CUDA-GGUF

Base model

LiquidAI/LFM2.5-2.6B-Base

Finetuned

LiquidAI/LFM2.5-2.6B

Quantized

LiquidAI/LFM2.5-2.6B-GGUF

Quantized

(3)

this model