GraySoft
Model Comparison

ggml-org/moondream2-20250414-ggufvsliquidai/lfm2-24b-a2b-gguf

Side-by-side comparison of ggml-org/moondream2-20250414-gguf and liquidai/lfm2-24b-a2b-gguf: downloads, license, context length, tasks, and benchmarks.

ggml-org/moondream2-20250414-gguf

ggml-org · —

This repo contains the llama.cpp compatible GGUFs of vikhyatk/moondream2: https://huggingface.co/vikhyatk/moondream2. The GGUFs hosted in the original repo is missing the tokenizer.chat_template field, thanks to @Hahasb for adding the vicuna template. For further discussion, ple…

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.

Side-by-side Specifications

ggml-org/moondream2-20250414-ggufliquidai/lfm2-24b-a2b-gguf
Authorggml-orgLiquidAI
Pipeline Tasktext-generation
Librarytransformers
Downloads18,80556,748
Likes12122
LicenseUnknownUnknown
Context Length
Created2025-05-252026-02-17
Last Modified2025-05-252026-03-30
Tags
ggufbase_model:vikhyatk/moondream2base_model:quantized:vikhyatk/moondream2license:apache-2.0endpoints_compatibleregion:usconversational
transformersggufliquidlfm2edgemoellama.cpptext-generationenar

View full details: ggml-org/moondream2-20250414-gguf · liquidai/lfm2-24b-a2b-gguf