LF

LFM2 700M

LfmGGUF by LiquidAIUpdated 2026-08-24
Download on Hugging Face
Parameters742M
Context125K
Layers16
Architecturelfm2
Smallest quant0.4 GB
Quick answer

LFM2 700M needs about 1.8 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.4 GB (Q4_0) to 1.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

LFM2 700M – a compact hybrid model for edge AI

LFM2 700M is a 0.7 billion‑parameter hybrid model from Liquid AI. It is optimized for fast training and inference on CPU, GPU, and NPU hardware. The model supports English, Arabic, Chinese, French, German, Japanese, Korean, and Spanish.

Good at

  • Fast CPU inference
  • Low memory footprint
  • Versatile on-device deployment

Limits

  • No vision support
  • Not suited for heavy knowledge or programming tasks
  • Requires fine‑tuning for narrow use cases

Best for

  • Agentic tasks
  • Data extraction
  • RAG and creative writing

Who it’s for. Developers building lightweight AI assistants or data‑processing agents on smartphones, laptops, or vehicles. The model is ideal for applications that need quick, low‑memory inference without extensive training data.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.4 GB 1.8 GB
Fits Get file →
Q4_K_M0.5 GB 1.8 GB
Fits Get file →
Q4_K_M0.5 GB 1.8 GB
Fits Get file →
Q5_K_M0.5 GB 1.8 GB
Fits Get file →
Q6_K0.6 GB 1.9 GB
Fits Get file →
Q8_00.8 GB 2.1 GB
Fits Get file →
F161.5 GB 2.8 GB
Fits Get file →

For 8 GB VRAM, Q4_0 or Q4_K_M (~0.45–0.47 GB) gives ~1.8 GB memory usage at 8 k context. If 12 GB VRAM is available, Q6_K (~0.61 GB) or Q8_0 (~0.79 GB) can be used for slightly higher quality. All estimates are approximate.

What GPU do you need for LFM2 700M?

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 (1.5 GB file, about 2.8 GB in use).

Which LFM2 700M quant should you choose?

Q4_K_M is the usual starting point for LFM2 700M: it balances file size and quality well. Here it is a 0.5 GB file.

The Q8_0 file is 0.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q4_0 at 0.4 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2
Parameters742M
Layers16
Trained context128,000 tokens
KV cache (fp16)96 KB per token

Source

Quantized byLiquidAI
FamilyLfm
Licenseother
Downloads (HF)13,481
Last updated2026-08-24

Frequently asked questions about LFM2 700M

How much VRAM does LFM2 700M need?

About 1.8 GB at Q4_K_M with an 8K context window. That is the 0.5 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 LFM2 700M on an 8 GB GPU?

Yes, with F16: the 1.5 GB file needs about 2.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LFM2 700M GGUF?

It depends on the quant: Q4_0 is 0.4 GB, Q4_K_M is 0.5 GB, Q4_K_M is 0.5 GB, Q5_K_M is 0.5 GB, Q6_K is 0.6 GB, Q8_0 is 0.8 GB and 1 more.

What context length does LFM2 700M support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download LFM2 700M GGUF?

The files are on Hugging Face in the LiquidAI/LFM2-700M-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 LFM2 700M use?

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

Can I run LFM2 700M on 8 GB VRAM?

Yes. The Q4_0 or Q4_K_M quantizations use about 1.8 GB of VRAM at 8 k context, leaving room for other processes.

Does LFM2 700M support vision tasks?

No. The model is text‑only and does not include vision capabilities.

What languages can LFM2 700M understand?

It supports English, Arabic, Chinese, French, German, Japanese, Korean, and Spanish.

Other GGUFs of LFM2-700M

Similar models

Browse all →

More from LiquidAI

All by LiquidAI →

More Lfm models

All Lfm →

Other tiny models

All tiny models →