LF

LFM2.5-24B-A2B-Preview

LfmGGUF by AtomicChatUpdated 2026-10-28
Download on Hugging Face
Parameters24B
Context128K
Layers40
Architecturelfm2moe
Smallest quant11.1 GB
Quick answer

LFM2.5-24B-A2B-Preview needs about 18.5 GB of memory at Q4_K_M (a 15.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 8 quants, from 11.1 GB (IQ3_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 2B active parameters

LFM2.5-24B-A2B is a 24.0B‑parameter mixture of experts model. It uses only 2.45B active parameters per token and supports a context length of 131,072 tokens. The model is designed for fast, private on‑device agents.

Good at

  • Reasoning with low active parameter cost
  • Fast on‑device inference
  • Tool‑calling and function execution

Limits

  • Requires large VRAM for higher‑bit quants
  • No vision support
  • License is other

Best for

  • On‑device reasoning agents
  • Tool‑calling workflows
  • Fast inference on high‑end GPUs

Who it’s for. Developers building private agents that need reasoning and tool use on device. The model is suitable for users with sufficient VRAM to run higher‑bit quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XXS11.1 GB 14.3 GB
Too big Get file →
IQ3_M12.1 GB 15.3 GB
Too big Get file →
IQ4_XS14.5 GB 17.7 GB
Too big Get file →
Q4_K_M15.4 GB 18.5 GB
Too big Get file →
Q5_K_M17.3 GB 20.5 GB
Too big Get file →
Q6_K20.9 GB 24.1 GB
Too big Get file →
Q8_025.7 GB 28.9 GB
Too big Get file →
BF1648.0 GB 51.1 GB
Too big Get file →

For 24 GB VRAM, use Q4_K_M (15.36 GB). For 32 GB, Q6_K (20.91 GB) is close to BF16. 3‑bit builds (IQ3_XXS, IQ3_M) fit below 16 GB but lose accuracy.

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is IQ3_M (12.1 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (17.3 GB file, about 20.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (25.7 GB file, about 28.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (25.7 GB file, about 28.9 GB in use).

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

Q4_K_M is the usual starting point for LFM2.5-24B-A2B-Preview: it balances file size and quality well. Here it is a 15.4 GB file.

The Q8_0 file is 25.7 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 IQ3_XXS at 11.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

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 byAtomicChat
FamilyLfm
Licenseother
Downloads (HF)3,988
Last updated2026-10-28

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

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

About 18.5 GB at Q4_K_M with an 8K context window. That is the 15.4 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 LFM2.5-24B-A2B-Preview on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.3 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: IQ3_XXS is 11.1 GB, IQ3_M is 12.1 GB, IQ4_XS is 14.5 GB, Q4_K_M is 15.4 GB, Q5_K_M is 17.3 GB, Q6_K is 20.9 GB and 2 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 AtomicChat/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?

The smallest quant (IQ3_XXS) requires 14.3 GB at 8 k context, so 8 GB VRAM is insufficient.

Does the model support vision?

No, it is a text‑only reasoning model.

What is the context length?

The model supports 131,072 tokens.

Other GGUFs of LFM2.5-24B-A2B

Similar models

Browse all →

More from AtomicChat

All by AtomicChat →

More Lfm models

All Lfm →

Other medium models

All medium models →