LF

LFM2.5 230M Distilled Gemini 3.8 Flash Uncensored

LfmGGUF by mradermacherUpdated 2026-09-04
Download on Hugging Face
Parameters230M
Context125K
Layers14
Architecturelfm2
Smallest quant0.1 GB
Quick answer

LFM2.5 230M Distilled Gemini 3.8 Flash Uncensored needs about 1.1 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.1 GB (Q2_K) to 0.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

LFM2.5 230M Distilled Gemini 3.8 Flash Uncensored – a small, reasoning‑capable LLM

This 230M‑parameter LLM is distilled from Gemini 3.8 Flash and abliterated to reduce refusal behavior. It supports reasoning and tool use. The model is released under Liquid AI’s license and requires compliance with Google Gemini API terms.

Good at

  • Reasoning
  • Tool use
  • Uncensored responses

Limits

  • No vision support
  • Large context requires 128k tokens
  • License restrictions for enterprise use

Best for

  • Chatbots needing reasoning
  • Tool‑enabled assistants
  • Research on alignment reduction

Who it’s for. Developers and researchers who need a lightweight, reasoning‑capable model with reduced safety alignment. Suitable for applications where compliance with the license and API terms is ensured.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.1 GB 1.1 GB
Fits Get file →
Q3_K_S0.1 GB 1.1 GB
Fits Get file →
Q3_K_M0.1 GB 1.1 GB
Fits Get file →
Q3_K_L0.1 GB 1.1 GB
Fits Get file →
IQ4_XS0.1 GB 1.1 GB
Fits Get file →
Q4_K_S0.1 GB 1.1 GB
Fits Get file →
Q4_K_M0.2 GB 1.1 GB
Fits Get file →
Q5_K_S0.2 GB 1.1 GB
Fits Get file →
Q5_K_M0.2 GB 1.1 GB
Fits Get file →
Q6_K0.2 GB 1.2 GB
Fits Get file →
Q8_00.2 GB 1.2 GB
Fits Get file →
F160.5 GB 1.4 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M (0.15 GB) or Q3_K_M (0.13 GB) are suitable, using about 1.1 GB of VRAM at 8k context. For 4 GB VRAM, Q2_K (0.12 GB) or IQ4_XS (0.14 GB) are recommended, with similar memory usage. Larger quantizations such as Q8_0 or F16 increase VRAM needs to 1.2–1.4 GB.

What GPU do you need for LFM2.5 230M Distilled Gemini 3.8 Flash 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 F16 (0.5 GB file, about 1.4 GB in use).

Which LFM2.5 230M Distilled Gemini 3.8 Flash Uncensored quant should you choose?

Q4_K_M is the usual starting point for LFM2.5 230M Distilled Gemini 3.8 Flash Uncensored: it balances file size and quality well. Here it is a 0.2 GB file.

The Q8_0 file is 0.2 GB, about 1.6 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 Q2_K at 0.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2
Parameters230M
Layers14
Trained context128,000 tokens
KV cache (fp16)56 KB per token

Frequently asked questions about LFM2.5 230M Distilled Gemini 3.8 Flash Uncensored

How much VRAM does LFM2.5 230M Distilled Gemini 3.8 Flash Uncensored need?

About 1.1 GB at Q4_K_M with an 8K context window. That is the 0.2 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 230M Distilled Gemini 3.8 Flash Uncensored on an 8 GB GPU?

Yes, with F16: the 0.5 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LFM2.5 230M Distilled Gemini 3.8 Flash Uncensored GGUF?

It depends on the quant: Q2_K is 0.1 GB, Q3_K_S is 0.1 GB, Q3_K_M is 0.1 GB, Q3_K_L is 0.1 GB, IQ4_XS is 0.1 GB, Q4_K_S is 0.1 GB and 6 more.

What context length does LFM2.5 230M Distilled Gemini 3.8 Flash Uncensored support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download LFM2.5 230M Distilled Gemini 3.8 Flash Uncensored GGUF?

The files are on Hugging Face in the mradermacher/LFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored-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 230M Distilled Gemini 3.8 Flash 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, using Q4_K_M or Q3_K_M quantizations will use approximately 1.1 GB of VRAM at 8k context.

Does this model support vision?

No, the model has no vision capabilities.

What license applies to this model?

It is released under Liquid AI’s license, free for individuals/companies under $10M annual revenue, with paid enterprise licensing above that.

Other GGUFs of LFM2.5-230M-distilled-Gemini-3.8-Flash-Uncensored

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Lfm models

All Lfm →

Other tiny models

All tiny models →