LF

LFM2.5 24B A2B Uncensored

LfmGGUF by mradermacherUpdated 2026-10-20
Download on Hugging Face
Parameters24B
Context128K
Layers40
Architecturelfm2moe
Smallest quant0.1 GB
Quick answer

LFM2.5 24B A2B Uncensored needs about 17.7 GB of memory at Q4_K_M (a 14.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.1 GB to 19.7 GB (Q6_K). 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 Uncensored is a text‑only reasoning model built for fast, private agents on device. It uses a mixture of experts architecture and supports tool‑use. The model has a 131,072‑token context length and is trained on 36 trillion tokens.

Good at

  • Reasoning before answering
  • Tool‑use support
  • Fast inference on device

Limits

  • Large VRAM requirement for higher‑quality quants
  • No vision support
  • License is other, not open source

Best for

  • On‑device private agents
  • Tool‑calling workflows
  • Long‑context reasoning tasks

Who it’s for. Developers building private agents that need reasoning and tool‑use capabilities on local hardware. Suitable for users who can allocate sufficient VRAM for the desired quantization level.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 3.3 GB
Fits Get file →
IQ1_S4.9 GB 8.1 GB
Too big Get file →
IQ1_M5.5 GB 8.7 GB
Too big Get file →
IQ2_XXS6.4 GB 9.6 GB
Too big Get file →
IQ2_XS7.1 GB 10.3 GB
Too big Get file →
IQ2_S7.2 GB 10.3 GB
Too big Get file →
IQ2_M7.9 GB 11.1 GB
Too big Get file →
Q2_K_S8.2 GB 11.4 GB
Too big Get file →
Q2_K8.8 GB 12.0 GB
Too big Get file →
IQ3_XXS9.3 GB 12.5 GB
Too big Get file →
IQ3_XS9.9 GB 13.0 GB
Too big Get file →
IQ3_S10.4 GB 13.6 GB
Too big Get file →
Q3_K_S10.4 GB 13.6 GB
Too big Get file →
IQ3_M10.5 GB 13.7 GB
Too big Get file →
Q3_K_M11.5 GB 14.7 GB
Too big Get file →
Q3_K_L12.4 GB 15.6 GB
Too big Get file →
IQ4_XS12.8 GB 16.0 GB
Too big Get file →
Q4_013.6 GB 16.8 GB
Too big Get file →
Q4_K_S13.7 GB 16.8 GB
Too big Get file →
Q4_K_M14.5 GB 17.7 GB
Too big Get file →
Q4_115.1 GB 18.2 GB
Too big Get file →
Q5_K_S16.5 GB 19.7 GB
Too big Get file →
Q5_K_M17.0 GB 20.2 GB
Too big Get file →
Q6_K19.7 GB 22.9 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (file size 4.93 GB, estimated memory 8.1 GB). For 12‑GB VRAM, IQ2_M (file size 7.88 GB, estimated memory 11.1 GB) or Q2_K (file size 8.81 GB, estimated memory 12 GB). For 16‑GB VRAM, Q4_K_M (file size 14.53 GB, estimated memory 17.7 GB) offers a balance of size and quality.

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

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: the best quant that fits is the main file (0.1 GB file, about 3.3 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 3.3 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 3.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q2_K (8.8 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ4_XS (12.8 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (19.7 GB file, about 22.9 GB in use).

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

Q4_K_M is the usual starting point for LFM2.5 24B A2B Uncensored: it balances file size and quality well. Here it is a 14.5 GB file.

If memory is tight, the smallest file is the first one in the table at 0.1 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
Parameters24B (approximate, mixture of experts)
Active parameters2B
Layers40
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyLfm
Licenseother
Downloads (HF)2,948
Last updated2026-10-20

Frequently asked questions about LFM2.5 24B A2B Uncensored

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

About 17.7 GB at Q4_K_M with an 8K context window. That is the 14.5 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 Uncensored on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: file is 0.1 GB, IQ1_S is 4.9 GB, IQ1_M is 5.5 GB, IQ2_XXS is 6.4 GB, IQ2_XS is 7.1 GB, IQ2_S is 7.2 GB and 18 more.

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

The files are on Hugging Face in the mradermacher/LFM2.5-24B-A2B-uncensored-i1-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 Uncensored 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 this model on 8 GB VRAM?

Yes, the IQ1_S quant requires about 8.1 GB of VRAM at 8 k context, which fits in 8 GB with some headroom.

Does this model support vision tasks?

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

What is the context length of this model?

The model supports a context length of 131,072 tokens.

Other GGUFs of LFM2.5-24B-A2B-uncensored

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Lfm models

All Lfm →

Other medium models

All medium models →