LF

LFM2 24B A2B APEX

LfmGGUF by mudlerUpdated 2026-08-17
Download on Hugging Face
Parameters23.8B
Context125K
Layers40
Architecturelfm2moe
Smallest quant9.5 GB
Quick answer

LFM2 24B A2B APEX needs about 18.5 GB of memory at its main file (a 15.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 7 quants, from 9.5 GB to 17.4 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

LFM2 24B A2B APEX – 24B MoE model with 2B active parameters per token

LFM2 24B A2B APEX is a 24B parameter Mixture-of-Experts model with only 2B active parameters per token. It supports 128000 context tokens and is optimized for on‑device inference. The model is available in GGUF format and can be run with llama.cpp, vLLM, or SGLang.

Good at

  • Fast edge inference
  • Efficient on consumer hardware
  • Supports function calling

Limits

  • No vision support
  • Requires large VRAM for full model
  • License is other

Best for

  • Agentic tool use
  • Offline document summarization
  • Local RAG pipelines

Who it’s for. Developers building privacy‑preserving, on‑premise chat or agent systems that need efficient inference on consumer laptops or desktops. The model is suitable for applications that require multilingual support and function calling.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—9.5 GB 12.7 GB
Too big Get file →
—11.5 GB 14.7 GB
Too big Get file →
—11.5 GB 14.7 GB
Too big Get file →
—15.3 GB 18.5 GB
Too big Get file →
—15.3 GB 18.5 GB
Too big Get file →
—17.4 GB 20.5 GB
Too big Get file →
—17.4 GB 20.5 GB
Too big Get file →

For 8‑GB VRAM, use the 9.5‑GB file (est. 12.7‑GB memory at 8k context). For 12‑GB VRAM, the 11.49‑GB file (est. 14.7‑GB memory) is suitable. For 16‑GB VRAM, the 15.28‑GB file (est. 18.5‑GB memory) fits. Memory estimates are approximate.

What GPU do you need for LFM2 24B A2B APEX?

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 (11.5 GB file, about 14.7 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (17.4 GB file, about 20.5 GB in use).

Which LFM2 24B A2B APEX quant should you choose?

If memory is tight, the smallest file is the first one in the table at 9.5 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
Parameters23.8B (approximate, mixture of experts)
Active parameters2B
Layers40
Trained context128,000 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymudler
FamilyLfm
Licenseother
Downloads (HF)1,074
Last updated2026-08-17

Frequently asked questions about LFM2 24B A2B APEX

How much VRAM does LFM2 24B A2B APEX need?

About 18.5 GB at its main file with an 8K context window. That is the 15.3 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 24B A2B APEX on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of LFM2 24B A2B APEX GGUF?

It depends on the quant: file is 9.5 GB, file is 11.5 GB, file is 11.5 GB, file is 15.3 GB, file is 15.3 GB, file is 17.4 GB and 1 more.

What context length does LFM2 24B A2B APEX support?

The GGUF header lists a trained context length of 128,000 tokens (125K). 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 24B A2B APEX GGUF?

The files are on Hugging Face in the mudler/LFM2-24B-A2B-APEX-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 24B A2B APEX 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 24B A2B APEX on 8 GB VRAM?

The smallest GGUF file is 9.5 GB, which requires about 12.7 GB of RAM at 8k context, so 8 GB VRAM is insufficient.

Does the model support vision tasks?

No, the model has no vision support.

What is the context length of this model?

The model was trained with 128000 context tokens.

Other GGUFs of LFM2-24B-A2B

Similar models

Browse all →

More from mudler

All by mudler →

More Lfm models

All Lfm →

Other medium models

All medium models →