Workflows/Code locally with LFM2.5-24B-A2B in VS Code + Cline

Coding / WORKFLOW

Code locally with LFM2.5-24B-A2B in VS Code + Cline

Serve LFM2.5-24B-A2B with llama.cpp, connect VS Code and Cline, and have it write a small module plus tests that you review and run yourself.

Verified sourceSource checked 11/9/2026

LOCAL

Freshness 88 out of 100. Release age: 32 days old, Oct 13, 2026. Measures age, not quality.

Popularity 63 out of 100. 35,825 downloads in 30 days; 613 lifetime likes. Checked Nov 13, 2026. Measures adoption, not quality.

What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

A new release starts at 100. The score halves every 180 days: 100 × 2^(−age in days / 180). When the release date is unavailable, a repository date is a fallback—not proof of when the model was released. Missing dates stay unscored.

Check the date source

Popularity · adoption

Downloads over the past 30 days carry 80% of the score; lifetime likes carry 20%. Both use a logarithmic scale, capped at 10 million downloads and 100,000 likes. If likes are unavailable, downloads carry all the weight. Missing download statistics stay unscored.

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Check the statistics source

Scores as of Nov 14, 2026. Statistics checked Nov 13, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

Before you begin

Hardware

Estimated from Liquid AI’s published file sizes plus runtime and context headroom. Only about 2.45B parameters are active per token, so partial offload to system RAM stays usable but slower. Not measured by YouRunAI.

Machine	LFM2.5-24B-A2B · Q4_K_M GGUF	LFM2.5-24B-A2B · Q8_0 GGUF
NVIDIA · 16 GB VRAM + 32 GB RAM	Runs with some layers offloaded to RAM; slower but usable	Heavy offload; choose Q4_K_M instead
NVIDIA RTX 4090 · 24 GB VRAM	Recommended start; fits on the GPU with the starting context	Does not fit fully; offload to RAM or use Q4_K_M
NVIDIA RTX 5090 · 32 GB VRAM	Comfortable, with room for longer context	Fits at the starting context; check free VRAM
AMD Radeon · 24 GB VRAM	Fits; requires the HIP or Vulkan llama.cpp build on Windows (Linux tab here is NVIDIA only)	Partial offload; requires the HIP or Vulkan build
Intel Arc · 16 GB VRAM + 32 GB RAM	Partial offload through the Vulkan llama.cpp build; slower	Heavy offload; choose Q4_K_M instead
Apple Silicon · 24 GB unified memory	Tight: close other apps and keep the starting context	Cannot fit; use Q4_K_M or a larger Mac
Apple Silicon · 32 GB unified memory	Recommended Mac start	Cannot fit in the default GPU memory budget; use Q4_K_M
Apple Silicon · 64 GB unified memory	Comfortable	Comfortable at the starting context
CPU only · 32 GB RAM	Runs on CPU; slow but usable for short tasks	Needs 48 GB RAM or more; use Q4_K_M

Both packages are Liquid AI’s own GGUF files. Liquid AI also publishes a 13.6 GB MLX 4-bit build for Apple Silicon; this guide uses llama.cpp on every platform so the same server works for chat, Cline and Hermes.

LOCAL CODING · VS CODE + CLINESOURCE-LINKED SETUP

Code locally with LFM2.5-24B-A2B in VS Code + Cline

Run Liquid AI’s GGUF in llama.cpp, connect Cline through its OpenAI-compatible provider, and have it create a function with tests. You review every edit and run the test yourself.

Choose a package Run its commands Check the result

BEFORE YOU BEGIN

Choose your package

Select the weights you want. The instructions, downloads and settings change with your choice.

The publisher has not provided a complete memory target for this task. Check its hardware guidance before starting.

CURRENT SETUP

LFM2.5-24B-A2B · Q4_K_M GGUF · official

Start at 32,768 tokens for this Cline coding setup. The 14.5 GB file is only the weights; the runtime and context add more memory. Longer context needs more memory, so reduce it first if the server runs out. Estimate, not a YouRunAI measurement.

Freshness 88 out of 100. Release age: 32 days old, Oct 13, 2026. Measures age, not quality.

Popularity 63 out of 100. 35,825 downloads in 30 days; 613 lifetime likes. Checked Nov 13, 2026. Measures adoption, not quality.

What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

Check the date source

Popularity · adoption

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Check the statistics source

Scores as of Nov 14, 2026. Statistics checked Nov 13, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

View weight source

THE WORKFLOW

Set up LFM2.5-24B-A2B · Q4_K_M GGUF on your machine

Choose your computer first, then its GPU path. The instructions below update to match your selection.

CHOOSE YOUR SETUPWindows

Install llama.cpp with winget

Open PowerShell and install the official llama.cpp release with winget, then close and reopen PowerShell so llama-server is on your PATH. The second command lists the compute devices llama.cpp can use. If only the CPU appears on an NVIDIA or AMD PC, download the CUDA or HIP Windows build from the official releases page instead, extract it, and run the same commands from that folder.

Official llama.cpp releases (Windows builds) Liquid AI GGUF package and run snippets

PowerShell

winget install llama.cpp
llama-server --list-devices

Download Q4_K_M and start the local server

In PowerShell, run this command and leave the window open. The first run downloads the 14.5 GB Q4_K_M file from Liquid AI's GGUF repository; later runs reuse it. The server listens only on this computer at http://127.0.0.1:8080, names the model lfm2.5-24b, and starts with a 32,768-token context and Liquid AI's recommended sampling (temperature 0.1, top_k 50, repetition penalty 1.05). Wait until the log says the server is listening.

Exact Q4_K_M file in the publisher repository llama.cpp server options

PowerShell

llama-server -hf LiquidAI/LFM2.5-24B-A2B-GGUF:Q4_K_M --alias lfm2.5-24b --jinja -c 32768 --temp 0.1 --top-k 50 --repeat-penalty 1.05 --host 127.0.0.1 --port 8080

Install VS Code, Cline and Node.js

Install Visual Studio Code, then open the Cline extension page and choose Install. Install the current Node.js LTS release as well; the example project uses Node’s built-in test runner, so no packages need to be downloaded.

Download Visual Studio Code Install the Cline extension Download Node.js LTS

Connect Cline to the local model

Open Cline's settings. Choose the OpenAI Compatible provider, set Base URL to http://127.0.0.1:8080/v1, enter any text such as local as the API key (llama.cpp does not check it), and set the model ID to lfm2.5-24b. Set the context window to 32768 so it matches the server. Keep auto-approve off for file edits and terminal commands.

Setting	Value
Provider	OpenAI Compatible
Base URL	http://127.0.0.1:8080/v1
Model ID	lfm2.5-24b
Context window	32768

Cline OpenAI-compatible provider settings

Create a small project and give Cline a coding task

Create an empty folder named lfm-coding-test, open it in VS Code with File → Open Folder, and paste the task below into Cline in Act mode. Approve each file write after reading it, and approve the single test command. Cline is the coding client; the model only proposes edits and commands.

Plain text

Create slugify.mjs that exports a function slugify(text) which lowercases text, trims it, replaces runs of non-alphanumeric characters with single hyphens and removes leading or trailing hyphens. Create slugify.test.mjs that uses node:test and node:assert to check at least four cases, including an empty string. Then run node --test and show me the result.

Review the diff and run the test yourself

Open both files and read the change. Then run the test from the VS Code terminal (PowerShell) to confirm it passes independently of Cline. A passing node --test run and code you have read is the result; a chat answer without saved files does not count.

PowerShell

node --test

SUCCESS CHECK · LFM2.5-24B-A2B · Q4_K_M GGUF

Reviewed code and a passing test

slugify.mjs and slugify.test.mjs exist in your project, you have read the diff, and node --test passes when you run it yourself.

Liquid AI trained LFM2.5-24B-A2B for agentic tool use and reports 51.0 on SWE-Bench Verified, below Qwen3.6-35B-A3B on the same card. Cline tool reliability with this exact package has not been tested by YouRunAI; keep approvals on.

Back to setup steps

When it doesn’t go to plan

Cline says the model returned no tool call or an invalid response.

Confirm the server was started with --jinja and the model ID is exactly lfm2.5-24b. Update llama.cpp, then retry the task. If it still fails, report the package and llama.cpp version rather than switching on auto-approve.

Cline reports the context window is exceeded.

Start a new Cline task, keep the project small, or restart the server with -c 65536 and set the same value in Cline if you have the memory.

node is not recognised.

Install Node.js LTS from nodejs.org, then close and reopen VS Code so its terminal picks up the new PATH.

REFERENCE LIBRARY

Sources and files

Original instructions, model files, and compatibility notes behind this setup.

5 SOURCES

01Liquid AI model card, license and recommended settingshuggingface.co 02Official LFM2.5-24B-A2B GGUF fileshuggingface.co 03llama.cpp releases and servergithub.com 04LFM Open License v1.0huggingface.co 05Cline OpenAI-compatible providerdocs.cline.bot

The model behind this workflow

LFM2.5-24B-A2B

Keep exploring

Text

SETUP GUIDE

Qwen3.5 · 9B private chat setup

Source-backed package and platform-route plan for private local chat with Qwen3.5 · 9B. Preserves the official Ollama 9B package, a smaller 4B family fallback, and a clearly labeled community uncensored GGUF option.

Freshness 37 out of 100. Release age: 260 days old, Feb 27, 2026. Measures age, not quality.

Build a private coding assistant with Qwen3.8 27B

Run Qwen3.8 27B with Ollama, connect it to Cline in VS Code, and make one reviewable code change in a tiny local project.

Freshness 68 out of 100. Repository age: 101 days old, Aug 5, 2026. Measures age, not quality.

Arena Open Source Web coding: rank 13 of 63. Ranked model: Qwen3.8-27B. Original model ranking, not a benchmark of this package. Export dated Nov 11, 2026. Source checked Nov 13, 2026. Human preference ranking, not hardware suitability.+3

SOFTWAREOllama + Visual Studio Code + Cline + Python

Create images locally with FLUX.2 Klein

Generate images from text prompts in ComfyUI with the fast distilled or more adjustable base 4B model. Save your results and reuse the visual workflow.

Freshness 31 out of 100. Release age: 303 days old, Jan 15, 2026. Measures age, not quality.

SOFTWAREComfyUI

LOCALRENTED GPU

Verified source