LF

LFM2.5-24B-A2B-Preview

LfmGGUF by unslothUpdated 2026-10-20
Download on Hugging Face
Parameters24B
Context128K
Layers40
Architecturelfm2moe
Smallest quant7.5 GB
Quick answer

LFM2.5-24B-A2B-Preview needs about 14.1 GB of memory at Q3_K_XL (a 10.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 10 quants, from 7.5 GB (IQ2_XXS) to 48.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

24B‑parameter reasoning model with only 2B active parameters for fast on‑device agents

LFM2.5-24B-A2B is a 24.0B‑parameter model that uses only 2.45B active parameters per token. It supports a 131,072‑token context and is optimized for reasoning and tool‑calling. The model is text‑only and designed for private, on‑device inference.

Good at

  • Fast reasoning with MoE speed
  • Efficient on‑device inference
  • Strong tool‑calling capability

Limits

  • Large context length requires significant VRAM
  • Not suitable for knowledge‑heavy tasks alone
  • No vision support

Best for

  • Building private reasoning agents
  • Tool‑enabled workflows on local hardware
  • On‑device inference with limited GPU memory

Who it’s for. Developers building private agents that need to reason and call tools efficiently on local devices. The model is ideal for on‑device inference where privacy and speed are priorities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS7.5 GB 10.7 GB
Too big Get file →
IQ2_M7.5 GB 10.7 GB
Too big Get file →
Q2_K_XL8.0 GB 11.2 GB
Too big Get file →
IQ3_XXS9.0 GB 12.1 GB
Too big Get file →
Q3_K_XL10.9 GB 14.1 GB
Too big Get file →
Q4_K_XL14.9 GB 18.1 GB
Too big Get file →
Q5_K_XL17.9 GB 21.1 GB
Too big Get file →
Q6_K_XL21.9 GB 25.0 GB
Too big Get file →
Q8_025.5 GB 28.7 GB
Too big Get file →
BF1648.0 GB 51.1 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS or IQ2_M (≈10.7 GB memory at 8 k context). For 12 GB VRAM, Q2_K_XL (≈11.2 GB). For 16 GB VRAM, Q3_K_XL (≈14.1 GB). Larger VRAM allows higher‑quality quants such as Q4_K_XL or Q5_K_XL.

What GPU do you need for LFM2.5-24B-A2B-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: the best quant that fits is Q2_K_XL (8.0 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_XL (10.9 GB file, about 14.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_XL (17.9 GB file, about 21.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (25.5 GB file, about 28.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (25.5 GB file, about 28.7 GB in use).

Which LFM2.5-24B-A2B-Preview quant should you choose?

Q3_K_XL (10.9 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ2_XXS at 7.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 byunsloth
FamilyLfm
Licenseother
Downloads (HF)171,061
Last updated2026-10-20

Frequently asked questions about LFM2.5-24B-A2B-Preview

How much VRAM does LFM2.5-24B-A2B-Preview need?

About 14.1 GB at Q3_K_XL with an 8K context window. That is the 10.9 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-Preview on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of LFM2.5-24B-A2B-Preview GGUF?

It depends on the quant: IQ2_XXS is 7.5 GB, IQ2_M is 7.5 GB, Q2_K_XL is 8.0 GB, IQ3_XXS is 9.0 GB, Q3_K_XL is 10.9 GB, Q4_K_XL is 14.9 GB and 4 more.

What context length does LFM2.5-24B-A2B-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-Preview GGUF?

The files are on Hugging Face in the unsloth/LFM2.5-24B-A2B-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 LFM2.5-24B-A2B-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 LFM2.5-24B-A2B on 8 GB VRAM?

Yes, with IQ2_XXS or IQ2_M quants the estimated memory is about 10.7 GB at 8 k context, which fits on 8 GB VRAM with some headroom.

Does the model support image input?

No, LFM2.5-24B-A2B is a text‑only model and does not handle vision inputs.

What context length does the model support?

The model supports up to 131,072 tokens of context.

Other GGUFs of LFM2.5-24B-A2B

Similar models

Browse all →

More from unsloth

All by unsloth →

More Lfm models

All Lfm →

Other medium models

All medium models →