LF

LFM2.5 24B A2B abliterated mixed

LfmGGUF by JakevinUpdated 2026-10-14
Download on Hugging Face
Parameters24B
Context128K
Layers40
Architecturelfm2moe
Smallest quant10.7 GB
Quick answer

LFM2.5 24B A2B abliterated mixed needs about 13.9 GB of memory at IQ3_M (a 10.7 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 only 2B active parameters

LFM2.5 24B A2B abliterated mixed is a text‑only reasoning model built for fast, private agents on device. It uses a mixture of experts architecture with 64 experts per block and top‑4 routing. The model supports function calling and has a context length of 131,072 tokens.

Good at

  • Fast on‑device reasoning
  • Efficient MoE inference
  • Tool‑calling with function definitions

Limits

  • Requires llama.cpp with lfm2moe support
  • No vision capabilities
  • License is other, not open source

Best for

  • Building private agents that need reasoning
  • Implementing tool‑calling workflows
  • Running on devices with limited GPU memory

Who it’s for. Developers who need a fast, private reasoning model for on‑device agents. The model is suitable for applications that benefit from tool‑calling and reasoning, but should be paired with retrieval or web search for knowledge‑heavy tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_M10.7 GB 13.9 GB
Too big Get file →

The IQ3_M quantization results in a 10.67 GB file and requires approximately 13.9 GB of VRAM at an 8 k context length. For 8 GB VRAM, a higher‑quantization such as Q4_K would be necessary, but that quant is not provided in the file list. For 16 GB VRAM, IQ3_M is suitable and offers a good balance of size and performance.

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

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 (10.7 GB file, about 13.9 GB in use).

Which LFM2.5 24B A2B abliterated mixed quant should you choose?

IQ3_M (10.7 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.

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 byJakevin
FamilyLfm
Licenseother
Downloads (HF)1,318
Last updated2026-10-14

Frequently asked questions about LFM2.5 24B A2B abliterated mixed

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

About 13.9 GB at IQ3_M with an 8K context window. That is the 10.7 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 abliterated mixed on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.9 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: IQ3_M is 10.7 GB.

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

The files are on Hugging Face in the Jakevin/LFM2.5-24B-A2B-abliterated-mixed-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 abliterated mixed 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 IQ3_M quantization requires about 13.9 GB of VRAM at 8 k context, so 8 GB VRAM is insufficient.

Does this model support vision?

No, it is a text‑only model and does not support vision.

What license does the model use?

The model is released under an other license, not an open source license.

Other GGUFs of LFM2.5-24B-A2B

Similar models

Browse all →

More from Jakevin

All by Jakevin →

More Lfm models

All Lfm →

Other medium models

All medium models →