Question 1

What is KoarAI/LFM2.5-350M-Thinking-0005-GGUF?

Accepted Answer

--- license: apache-2.0 language: - ru - en tags: - liquid-ai - lfm2.5 - reasoning - gguf - llama-cpp - ollama ---

# 🧠 LFM2.5-350M-Thinking-0005-GGUF Quantized GGUF binaries of **KoarAI/LFM2.5-350M-Thinking-0005** for ultra-fast local inference on CPU, Vulkan, and Apple Metal via `llama.cpp`. ## 📦 Available Files | File | Precision | Size | Description | |---|---|---|---| | `LFM2.5-350M-Thinking-0005-f16.gguf` | FP16 | ~709 MB | Full precision golden baseline | | `LFM2.5-350M-Thinking-0005-q8_0.gguf` | Q8_0 | ~380 MB | High-quality quantized balance | ## 🚀 Quick Start (llama.cpp) ```bash llama-cli -m LFM2.5-350M-Thinking-0005-f16.gguf -p "<|im_start|>user Сколько букв 'р' в слове 'трапеция'? Разбери пошагово. <|im_end|> <|im_start|>assistant " -n 512 --temp 0.6 ```

Question 2

What license applies to KoarAI/LFM2.5-350M-Thinking-0005-GGUF?

Accepted Answer

License: apache-2.0. Verify terms on Hugging Face before commercial use.

Question 3

How do I run KoarAI/LFM2.5-350M-Thinking-0005-GGUF locally?

Accepted Answer

Download a GGUF file from this page and load it in guIDE or llama.cpp. Pipeline task: text-generation.

Question 4

How much VRAM or disk space does KoarAI/LFM2.5-350M-Thinking-0005-GGUF need?

Accepted Answer

Runs locally from ~360.5 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Model ID	KoarAI/LFM2.5-350M-Thinking-0005-GGUF
Author	KoarAI
Pipeline	—
License	apache-2.0
Base model	—
Last modified	2026-08-31T15:05:57.000Z

KoarAI/LFM2.5-350M-Thinking-0005-GGUF overview

Repository Files & Downloads

Model Details

Model README

🧠 LFM2.5-350M-Thinking-0005-GGUF

📦 Available Files

🚀 Quick Start (llama.cpp)

Run KoarAI/LFM2.5-350M-Thinking-0005-GGUF with guIDE

File	Type	Quantization	Size	Link
LFM2.5-350M-Thinking-0005-f16.gguf	GGUF	F16	676.3 MB	Download
LFM2.5-350M-Thinking-0005-q8_0.gguf	GGUF	Q8_0	360.5 MB	Download