GraySoft
Download guIDE →
Model Comparison

liquidai/lfm2-24b-a2b-ggufvsunsloth/qwen3.5-2b-gguf

Side-by-side comparison of liquidai/lfm2-24b-a2b-gguf and unsloth/qwen3.5-2b-gguf: downloads, license, context length, tasks, and benchmarks.

liquidai/lfm2-24b-a2b-gguf

LiquidAI · text-generation

LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion parameters while keeping inference efficient. !image Find more information about LFM2-24B-A2B in our blog post.

unsloth/qwen3.5-2b-gguf

unsloth · image-text-to-text

![Qwen Chat](https://chat.qwen.ai) > [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc. …

Side-by-side Specifications

liquidai/lfm2-24b-a2b-ggufunsloth/qwen3.5-2b-gguf
AuthorLiquidAIunsloth
Pipeline Tasktext-generationimage-text-to-text
Librarytransformerstransformers
Downloads56,748334,414
Likes12293
LicenseUnknownUnknown
Context Length——
Created2026-02-172026-02-28
Last Modified2026-03-302026-03-02
Tags
transformersggufliquidlfm2edgemoellama.cpptext-generationenar
transformersggufunslothimage-text-to-textbase_model:Qwen/Qwen3.5-2Bbase_model:quantized:Qwen/Qwen3.5-2Blicense:apache-2.0endpoints_compatibleregion:usconversational

View full details: liquidai/lfm2-24b-a2b-gguf · unsloth/qwen3.5-2b-gguf