Model Comparison

liquidai/lfm2-24b-a2b-ggufvsunsloth/nemotron-3-nano-30b-a3b-gguf

Side-by-side comparison of liquidai/lfm2-24b-a2b-gguf and unsloth/nemotron-3-nano-30b-a3b-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/nemotron-3-nano-30b-a3b-gguf

unsloth · text-generation

![](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16/resolve/main/accuracy_chart.png)

Side-by-side Specifications

	liquidai/lfm2-24b-a2b-gguf	unsloth/nemotron-3-nano-30b-a3b-gguf
Author	LiquidAI	unsloth
Pipeline Task	text-generation	text-generation
Library	transformers	transformers
Downloads	56,748	210,458
Likes	122	290
License	Unknown	Unknown
Context Length	—	—
Created	2026-02-17	2025-12-15
Last Modified	2026-03-30	2025-12-31
Tags	transformersggufliquidlfm2edgemoellama.cpptext-generationenar	transformersggufnvidiaunslothtext-generationenesfrdeja

View full details: liquidai/lfm2-24b-a2b-gguf · unsloth/nemotron-3-nano-30b-a3b-gguf