LF

LFM2.5 8B A1B MXFP4 MOE

LfmGGUF by noctrexUpdated 2026-06-02
Download on Hugging Face
Parameters8.47B
Context125K
Layers24
Architecturelfm2moe
Smallest quant5.1 GB
Quick answer

LFM2.5 8B A1B MXFP4 MOE needs about 7.7 GB of memory at MXFP4_MOE (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 5.1 GB (MXFP4_MOE) to 9.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

LFM2.5 8B A1B MXFP4 MOE is a 8.47B-parameter Lfm model in GGUF format, quantized by noctrex. Its trained context length is 125K tokens. The repository has 4 quant files, from 5.1 GB (MXFP4_MOE) to 9.7 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE5.1 GB 7.2 GB
Tight Get file →
MXFP4_MOE5.6 GB 7.7 GB
Tight Get file →
MXFP4_MOE5.6 GB 7.7 GB
Tight Get file →
—9.7 GB 11.8 GB
Too big Get file →

What GPU do you need for LFM2.5 8B A1B MXFP4 MOE?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is MXFP4_MOE (5.6 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (9.7 GB file, about 11.8 GB in use).

Which LFM2.5 8B A1B MXFP4 MOE quant should you choose?

MXFP4_MOE (5.6 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

If memory is tight, the smallest file is MXFP4_MOE at 5.1 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2moe
Parameters8.47B (approximate, mixture of experts)
Active parameters1B
Layers24
Trained context128,000 tokens
KV cache (fp16)192 KB per token

Source

Quantized bynoctrex
FamilyLfm
Licenseother
Downloads (HF)158
Last updated2026-06-02

Frequently asked questions about LFM2.5 8B A1B MXFP4 MOE

How much VRAM does LFM2.5 8B A1B MXFP4 MOE need?

About 7.7 GB at MXFP4_MOE with an 8K context window. That is the 5.6 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 LFM2.5 8B A1B MXFP4 MOE on an 8 GB GPU?

Yes, with MXFP4_MOE: the 5.6 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LFM2.5 8B A1B MXFP4 MOE GGUF?

It depends on the quant: MXFP4_MOE is 5.1 GB, MXFP4_MOE is 5.6 GB, MXFP4_MOE is 5.6 GB, file is 9.7 GB.

What context length does LFM2.5 8B A1B MXFP4 MOE support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download LFM2.5 8B A1B MXFP4 MOE GGUF?

The files are on Hugging Face in the noctrex/LFM2.5-8B-A1B-MXFP4_MOE-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 LFM2.5 8B A1B MXFP4 MOE 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.

Other GGUFs of LFM2.5-8B-A1B

Similar models

Browse all →

More from noctrex

All by noctrex →

More Lfm models

All Lfm →

Other small models

All small models →