MO

Models KoarAI LFM2.5 350M Thinking 0005

ModelsGGUF by KoarAIUpdated 2026-08-31
Download on Hugging Face
Parameters353M
Context125K
Layers16
Architecturelfm2
Smallest quant0.4 GB
Quick answer

Models KoarAI LFM2.5 350M Thinking 0005 needs about 1.4 GB of memory at Q8_0 (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.4 GB (Q8_0) to 0.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.

Models KoarAI LFM2.5 350M Thinking 0005 is a 353M-parameter Models model in GGUF format, quantized by KoarAI. Its trained context length is 125K tokens. The repository has 2 quant files, from 0.4 GB (Q8_0) to 0.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.4 GB 1.4 GB
Fits Get file →
F160.7 GB 1.7 GB
Fits Get file →

What GPU do you need for Models KoarAI LFM2.5 350M Thinking 0005?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is F16 (0.7 GB file, about 1.7 GB in use).

Which Models KoarAI LFM2.5 350M Thinking 0005 quant should you choose?

Q8_0 (0.4 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2
Parameters353M
Layers16
Trained context128,000 tokens
KV cache (fp16)64 KB per token

Source

Quantized byKoarAI
FamilyModels
Licenseapache-2.0
Downloads (HF)48
Last updated2026-08-31

Frequently asked questions about Models KoarAI LFM2.5 350M Thinking 0005

How much VRAM does Models KoarAI LFM2.5 350M Thinking 0005 need?

About 1.4 GB at Q8_0 with an 8K context window. That is the 0.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Models KoarAI LFM2.5 350M Thinking 0005 on an 8 GB GPU?

Yes, with F16: the 0.7 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Models KoarAI LFM2.5 350M Thinking 0005 GGUF?

It depends on the quant: Q8_0 is 0.4 GB, F16 is 0.7 GB.

What context length does Models KoarAI LFM2.5 350M Thinking 0005 support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.

Where can I download Models KoarAI LFM2.5 350M Thinking 0005 GGUF?

The files are on Hugging Face in the KoarAI/LFM2.5-350M-Thinking-0005-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Models KoarAI LFM2.5 350M Thinking 0005 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from KoarAI

All by KoarAI →

More Models models

All Models →

Other tiny models

All tiny models →