LF

LFM2.5-24B-A2B

LfmGGUF by IsValorumUpdated 2026-10-26
Download on Hugging Face
Parameters24B
Context128K
Layers40
Architecturelfm2moe
Smallest quant9.6 GB
Quick answer

LFM2.5-24B-A2B needs about 12.8 GB of memory at its main file (a 9.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. 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 reasoning model with only 2.45B active parameters. It is designed for fast, private on-device agents and supports tool calling. The model has a 131072-token context length and uses a mixture-of-experts architecture.

Good at

  • Reasoning before answering
  • Tool calling
  • Efficient inference on-device

Limits

  • Large VRAM requirement (~12.8GB at 8k context)
  • No vision support
  • Requires 131072-token context

Best for

  • On-device private agents
  • Tool‑enabled workflows
  • Reasoning‑heavy tasks

Who it’s for. Developers building private agents that need to reason and call tools locally. The model is suitable for users who can allocate sufficient VRAM and want a pure reasoning model without knowledge‑heavy tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—9.6 GB 12.8 GB
Too big Get file →

The available quantization is "unknown" with a file size of 9.64 GB. It requires approximately 12.8 GB of VRAM at an 8 k context length. For lower memory budgets, no other quantizations are listed, so this is the recommended build.

What GPU do you need for LFM2.5-24B-A2B?

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 (9.6 GB file, about 12.8 GB in use).

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 byIsValorum
FamilyLfm
Licenseother
Downloads (HF)1,873
Last updated2026-10-26

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

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

About 12.8 GB at its main file with an 8K context window. That is the 9.6 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 LFM2.5-24B-A2B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.8 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: file is 9.6 GB.

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

The files are on Hugging Face in the IsValorum/LFM2.5-24B-A2B-APEX-I-MiniPlus-V2.1-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 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?

No. The model requires about 12.8 GB of VRAM at an 8 k context length.

Does LFM2.5-24B-A2B support vision?

No, it is a text‑only model.

What is the maximum context length?

The model supports 131072 tokens.

Other GGUFs of LFM2.5-24B-A2B

Similar models

Browse all →

More from IsValorum

All by IsValorum →

More Lfm models

All Lfm →

Other medium models

All medium models →