LiquidAI/LFM2-350M

Name: LiquidAI/LFM2-350M
Author: LiquidAI

Run locally on Apple devices with Mirai

Type: local
From: LiquidAI
Quantization: No
Parameters: 350M
Size: 680.8 MB
Source

Automated benchmark results

LFM2-350M

LFM2-350M is the smallest model in Liquid AI's second-generation LFM2 family, a series of hybrid language models purpose-built for edge AI and on-device deployment. With roughly 354 million parameters, it delivers a compelling balance of quality, speed, and memory efficiency for resource-constrained environments.

Architecture & Training

LFM2-350M introduces a novel hybrid architecture combining multiplicative gates and short convolutions — specifically 10 double-gated short-range LIV convolution blocks and 6 grouped query attention (GQA) blocks across 16 layers. It supports a 32,768-token context window with a 65,536-token vocabulary in bfloat16 precision.

The model was trained on 10 trillion tokens (approximately 75% English, 20% multilingual, 5% code) using knowledge distillation from LFM1-7B, large-scale supervised fine-tuning, custom DPO with length normalization, and iterative model merging. It supports eight languages: English, Arabic, Chinese, French, German, Japanese, Korean, and Spanish.

Performance

LFM2 models outperform similarly sized competitors across knowledge, math, instruction following, and multilingual benchmarks. The family also achieves up to 2× faster decode and prefill on CPU compared to Qwen3.

Liquid AI

LLM-as-a-Judge evaluation

LLM-as-a-Judge detail

Inference throughput comparisons demonstrate strong performance across CPU runtimes:

CPU throughput — ExecuTorch

CPU throughput — llama.cpp

Best Use Cases

Due to its compact size, Liquid AI recommends fine-tuning LFM2-350M on narrow tasks for best results. It is well suited for agentic workflows, data extraction, RAG pipelines, creative writing, and multi-turn conversations. It also supports structured tool use via JSON function definitions. Deployment is flexible across CPU, GPU, and NPU hardware — ideal for smartphones, laptops, and vehicles.

Compatible with Hugging Face Transformers (v4.55+), vLLM, and llama.cpp via GGUF. Licensed under LFM Open License v1.0.

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: "LiquidAI/LFM2-350M") 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: "LiquidAI/LFM2-350M") 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	}