GraySoft
Model Comparison

liquidai/lfm2-24b-a2b-ggufvsmradermacher/apertus-70b-instruct-2509-heretic-v3-i1-gguf

Side-by-side comparison of liquidai/lfm2-24b-a2b-gguf and mradermacher/apertus-70b-instruct-2509-heretic-v3-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/apertus-70b-instruct-2509-heretic-v3-i1-gguf

mradermacher · —

## About weighted/imatrix quants of https://huggingface.co/surelio/Apertus-70B-Instruct-2509-heretic-v1.1.3 ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/Apertus-70B-Inst…

Side-by-side Specifications

liquidai/lfm2-24b-a2b-ggufmradermacher/apertus-70b-instruct-2509-heretic-v3-i1-gguf
AuthorLiquidAImradermacher
Pipeline Tasktext-generation
Librarytransformerstransformers
Downloads56,74819,855
Likes1220
LicenseUnknownUnknown
Context Length
Created2026-02-172026-04-03
Last Modified2026-03-302026-04-08
Tags
transformersggufliquidlfm2edgemoellama.cpptext-generationenar
transformersggufmultilingualcompliantswiss-aiapertushereticuncensoreddecensoredabliterated

View full details: liquidai/lfm2-24b-a2b-gguf · mradermacher/apertus-70b-instruct-2509-heretic-v3-i1-gguf