mlx-community/LFM2-2.6B-4bit

Name: mlx-community/LFM2-2.6B-4bit
Author: LiquidAI

Run locally on Apple devices with Mirai

Type: local
From: LiquidAI
Quantization: MLX 4-bit
Parameters: 2.6B
Size: 1.4 GB
Source

A 4-bit quantized version of LiquidAI's LFM2-2.6B, converted to Apple's MLX format for efficient on-device inference on Apple Silicon hardware. This community conversion was produced using `mlx-lm` v0.28.0.

Origin & Architecture

LFM2-2.6B is developed by Liquid AI as part of their LFM2 (Liquid Foundation Model) family, purpose-built for edge deployment. The model is compact at 2.6 billion parameters, and the 4-bit quantization further reduces memory footprint and accelerates inference — making it well-suited for local use on Mac devices without requiring cloud resources.

Multilingual Text Generation

The model supports text generation across eight languages:

English, French, German, Spanish
Arabic, Chinese, Japanese, Korean

This broad multilingual coverage in a small, quantized package makes it a practical choice for on-device applications that need to handle diverse language inputs.

Key Strengths

Edge-optimized: Designed from the ground up for resource-constrained environments, combining a small parameter count with aggressive quantization.
MLX-native: Runs natively on Apple Silicon via the MLX framework, leveraging unified memory and GPU acceleration on M-series chips.
Low barrier to use: Compatible with the `mlx-lm` Python library, supporting chat templates and standard generation workflows out of the box.

Use Cases

LFM2-2.6B-4bit is a strong fit for local chatbots, lightweight multilingual assistants, text summarization, and any scenario where low-latency, private, on-device inference is preferred over cloud-based API calls. Its small size makes it especially appealing for developers prototyping on laptops or deploying to edge hardware.

> License: Released under the LFM 1.0 license from Liquid AI. Review the license terms before commercial use.

Explore all local models

Choose framework

Run the following command to install Mirai SDK

spm https://github.com/trymirai/uzu.git

Apply code

1import Uzu23public func runChat() async throws {4    let engineConfig = EngineConfig.create()5    let engine = try await Engine.create(config: engineConfig)67    guard let model = try await engine.model(identifier: "mlx-community/LFM2-2.6B-4bit") else {8        return9    }10    for try await update in try await engine.download(model: model).iterator() {11        print("Download progress: \(update.progress())")12    }1314    let messages = [15        ChatMessage.system().withText(text: "You are a helpful assistant"),16        ChatMessage.user().withText(text: "Tell me a short, funny story about a robot")17    ]18    let session = try await engine.chat(model: model, config: .create())19    let stream = await session.replyWithStream(input: messages, config: .create())20    var message: ChatMessage? = nil21    for try await update in stream.iterator() {22        switch update {23        case .replies(let replies):24            message = replies.last?.message25        case .error(let error):26            print("Error: \(error)")27        }28    }29    print("Text: \(message?.text() ?? "empty")")30}

1Choose framework

2Run the following command to install Mirai SDK

spm https://github.com/trymirai/uzu.git

3Apply code

1	import Uzu
2
3	public func runChat() async throws {
4	let engineConfig = EngineConfig.create()
5	let engine = try await Engine.create(config: engineConfig)
6
7	guard let model = try await engine.model(identifier: "mlx-community/LFM2-2.6B-4bit") else {
8	return
9	}
10	for try await update in try await engine.download(model: model).iterator() {
11	print("Download progress: \(update.progress())")
12	}
13
14	let messages = [
15	ChatMessage.system().withText(text: "You are a helpful assistant"),
16	ChatMessage.user().withText(text: "Tell me a short, funny story about a robot")
17	]
18	let session = try await engine.chat(model: model, config: .create())
19	let stream = await session.replyWithStream(input: messages, config: .create())
20	var message: ChatMessage? = nil
21	for try await update in stream.iterator() {
22	switch update {
23	case .replies(let replies):
24	message = replies.last?.message
25	case .error(let error):
26	print("Error: \(error)")
27	}
28	}
29	print("Text: \(message?.text() ?? "empty")")
30	}