GraySoft
Model Comparison

liquidai/lfm2-24b-a2b-ggufvsmradermacher/aum-1-70b-i1-gguf

Side-by-side comparison of liquidai/lfm2-24b-a2b-gguf and mradermacher/aum-1-70b-i1-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.

mradermacher/aum-1-70b-i1-gguf

mradermacher · —

## About weighted/imatrix quants of https://huggingface.co/Nitish-Garikoti/aum-1-70B ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/aum-1-70B-GGUF

Side-by-side Specifications

liquidai/lfm2-24b-a2b-ggufmradermacher/aum-1-70b-i1-gguf
AuthorLiquidAImradermacher
Pipeline Tasktext-generation
Librarytransformerstransformers
Downloads56,74831,795
Likes1220
LicenseUnknownUnknown
Context Length
Created2026-02-172026-03-31
Last Modified2026-03-302026-04-03
Tags
transformersggufliquidlfm2edgemoellama.cpptext-generationenar
transformersggufllamathinkingreasoningdistillationsftpytorchenbase_model:Nitish-Garikoti/aum-1-70B

View full details: liquidai/lfm2-24b-a2b-gguf · mradermacher/aum-1-70b-i1-gguf