GraySoft
Model Comparison

liquidai/lfm2-24b-a2b-ggufvsunsloth/minimax-m2.5-gguf

Side-by-side comparison of liquidai/lfm2-24b-a2b-gguf and unsloth/minimax-m2.5-gguf: downloads, license, context length, tasks, and benchmarks.

liquidai/lfm2-24b-a2b-gguf

LiquidAI ยท 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/minimax-m2.5-gguf

unsloth ยท text-generation

To Run MiniMax-M2.5 locally - Read our Guide! Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants. --- Join Our ๐Ÿ’ฌ WeChat | ๐Ÿงฉ Discord community. MiniMax Agent | โšก๏ธ API | MCP | MiniMax Website ๐Ÿค— Hugging Face | ๐Ÿš€ Hugging Face API | ๐Ÿ™ GitHub | ๐Ÿค–๏ธ โ€ฆ

Side-by-side Specifications

liquidai/lfm2-24b-a2b-ggufunsloth/minimax-m2.5-gguf
AuthorLiquidAIunsloth
Pipeline Tasktext-generationtext-generation
Librarytransformerstransformers
Downloads56,74884,669
Likes122231
LicenseUnknownUnknown
Context Lengthโ€”โ€”
Created2026-02-172026-02-14
Last Modified2026-03-302026-02-14
Tags
transformersggufliquidlfm2edgemoellama.cpptext-generationenar
transformersggufunslothminimax_m2text-generationbase_model:MiniMaxAI/MiniMax-M2.5base_model:quantized:MiniMaxAI/MiniMax-M2.5license:otherendpoints_compatibleregion:us

View full details: liquidai/lfm2-24b-a2b-gguf · unsloth/minimax-m2.5-gguf