LF

LFM2.5 24B A2B Nyquant Q4 preview

LfmGGUF by XGeorgeCostanzaXUpdated 2026-10-23
Download on Hugging Face
Parameters24B
Context128K
Layers40
Architecturelfm2moe
Smallest quant12.0 GB
Quick answer

LFM2.5 24B A2B Nyquant Q4 preview needs about 16.3 GB of memory at its main file (a 13.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 12.0 GB to 13.9 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

LFM2.5 24B A2B Nyquant Q4 preview – a 24B reasoning model with 2B active parameters

LFM2.5 24B A2B Nyquant Q4 preview is a 24.0B‑parameter reasoning model with only 2.45B active parameters. It supports a 131,072‑token context and is designed for fast, private on‑device agents. The model is a mixture of experts with 64 experts per block and top‑4 routing.

Good at

  • Fast on‑device reasoning
  • Efficient MoE inference
  • Tool‑calling support

Limits

  • Large VRAM requirement
  • No vision support
  • Requires llama.cpp for inference

Best for

  • Private agent development
  • Tool‑enabled chatbots
  • On‑device reasoning tasks

Who it’s for. Developers building private agents that need reasoning and tool‑calling on local hardware. The model is suitable for users who can allocate sufficient VRAM and prefer a pure text‑only reasoning engine.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—12.0 GB 15.2 GB
Too big Get file →
—13.1 GB 16.3 GB
Too big Get file →
—13.9 GB 17.1 GB
Too big Get file →

For 8 GB VRAM, the 12 GB file (est. 15.2 GB at 8 k context) is the smallest but still exceeds typical GPU limits; a 13.08 GB file (16.3 GB) or 13.87 GB file (17.1 GB) will need more memory. Choose the file that fits your GPU budget, noting the estimates are approximate.

What GPU do you need for LFM2.5 24B A2B Nyquant Q4 preview?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is the main file (12.0 GB file, about 15.2 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (13.9 GB file, about 17.1 GB in use).

Which LFM2.5 24B A2B Nyquant Q4 preview quant should you choose?

If memory is tight, the smallest file is the first one in the table at 12.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2moe
Parameters24B (approximate, mixture of experts)
Active parameters2B
Layers40
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized byXGeorgeCostanzaX
FamilyLfm
Licenseother
Downloads (HF)3,575
Last updated2026-10-23

Frequently asked questions about LFM2.5 24B A2B Nyquant Q4 preview

How much VRAM does LFM2.5 24B A2B Nyquant Q4 preview need?

About 16.3 GB at its main file with an 8K context window. That is the 13.1 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 24B A2B Nyquant Q4 preview on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of LFM2.5 24B A2B Nyquant Q4 preview GGUF?

It depends on the quant: file is 12.0 GB, file is 13.1 GB, file is 13.9 GB.

What context length does LFM2.5 24B A2B Nyquant Q4 preview support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download LFM2.5 24B A2B Nyquant Q4 preview GGUF?

The files are on Hugging Face in the XGeorgeCostanzaX/LFM2.5-24B-A2B-Nyquant-Q4-preview 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 24B A2B Nyquant Q4 preview 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 this model on an 8 GB GPU?

The smallest file is 12 GB, estimating 15.2 GB at 8 k context, so it will not fit on an 8 GB GPU. You would need a GPU with more VRAM.

Does this model support vision?

No, it is a text‑only reasoning model with no vision capabilities.

What is the context length of this model?

The model supports a context length of 131,072 tokens.

Other GGUFs of LFM2.5-24B-A2B

Similar models

Browse all →

More from XGeorgeCostanzaX

All by XGeorgeCostanzaX →

More Lfm models

All Lfm →

Other medium models

All medium models →