LF

LFM2.5 1.2B Thinking Abliterated

LfmGGUF by mradermacherUpdated 2026-07-18
Download on Hugging Face
Parameters1.17B
Context125K
Layers16
Architecturelfm2
Smallest quant0.0 GB
Quick answer

LFM2.5 1.2B Thinking Abliterated needs about 2.3 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 1.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

LFM2.5 1.2B Thinking Abliterated – a 1.17B parameter model with refusal circuitry removed

LFM2.5 1.2B Thinking Abliterated is a 1.17B parameter model based on LFM2 architecture. It has been modified to remove refusal circuitry while maintaining coherence on benign queries. The model supports reasoning and tool usage.

Good at

  • Reasoning tasks
  • Tool integration
  • Direct actionable responses

Limits

  • No vision support
  • Requires 128000 token context
  • Apache‑2.0 license

Best for

  • Research on refusal mechanisms
  • Testing thinking models
  • Educational demonstrations

Who it’s for. Researchers and developers interested in studying refusal mechanisms in thinking models. The model is released for research purposes only.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.6 GB
Fits Get file →
IQ1_S0.3 GB 1.9 GB
Fits Get file →
IQ1_M0.3 GB 1.9 GB
Fits Get file →
IQ2_XXS0.4 GB 1.9 GB
Fits Get file →
IQ2_XS0.4 GB 2.0 GB
Fits Get file →
IQ2_S0.4 GB 2.0 GB
Fits Get file →
IQ2_M0.4 GB 2.0 GB
Fits Get file →
Q2_K_S0.5 GB 2.0 GB
Fits Get file →
Q2_K0.5 GB 2.1 GB
Fits Get file →
IQ3_XXS0.5 GB 2.1 GB
Fits Get file →
IQ3_XS0.5 GB 2.1 GB
Fits Get file →
IQ3_S0.6 GB 2.1 GB
Fits Get file →
Q3_K_S0.6 GB 2.1 GB
Fits Get file →
IQ3_M0.6 GB 2.1 GB
Fits Get file →
Q3_K_M0.6 GB 2.2 GB
Fits Get file →
Q3_K_L0.6 GB 2.2 GB
Fits Get file →
IQ4_XS0.7 GB 2.2 GB
Fits Get file →
IQ4_NL0.7 GB 2.3 GB
Fits Get file →
Q4_00.7 GB 2.3 GB
Fits Get file →
Q4_K_S0.7 GB 2.3 GB
Fits Get file →
Q4_K_M0.7 GB 2.3 GB
Fits Get file →
Q4_10.8 GB 2.3 GB
Fits Get file →
Q5_K_S0.8 GB 2.4 GB
Fits Get file →
Q5_K_M0.8 GB 2.4 GB
Fits Get file →
Q6_K1.0 GB 2.5 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.73 GB file, ~2.3 GB memory). For 6 GB VRAM, use IQ2_XS (0.4 GB file, ~2 GB memory). For 4 GB VRAM, use IQ1_S (0.3 GB file, ~1.9 GB memory). Memory estimates are approximate.

What GPU do you need for LFM2.5 1.2B Thinking Abliterated?

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 Q6_K (1.0 GB file, about 2.5 GB in use).

Which LFM2.5 1.2B Thinking Abliterated quant should you choose?

Q4_K_M is the usual starting point for LFM2.5 1.2B Thinking Abliterated: it balances file size and quality well. Here it is a 0.7 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 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

Architecturelfm2
Parameters1.17B
Layers16
Trained context128,000 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyLfm
Licenseapache-2.0
Downloads (HF)523
Last updated2026-07-18

Frequently asked questions about LFM2.5 1.2B Thinking Abliterated

How much VRAM does LFM2.5 1.2B Thinking Abliterated need?

About 2.3 GB at Q4_K_M with an 8K context window. That is the 0.7 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 1.2B Thinking Abliterated on an 8 GB GPU?

Yes, with Q6_K: the 1.0 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LFM2.5 1.2B Thinking Abliterated GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 0.3 GB, IQ1_M is 0.3 GB, IQ2_XXS is 0.4 GB, IQ2_XS is 0.4 GB, IQ2_S is 0.4 GB and 19 more.

What context length does LFM2.5 1.2B Thinking Abliterated support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download LFM2.5 1.2B Thinking Abliterated GGUF?

The files are on Hugging Face in the mradermacher/LFM2.5-1.2B-Thinking-Abliterated-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 1.2B Thinking Abliterated use?

Hugging Face lists the license as apache-2.0. 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 Q4_K_M quant uses about 2.3 GB memory at 8 k context, which fits in 8 GB VRAM.

Does the model support vision?

No, the model has no vision capabilities.

What license applies?

The model is released under the Apache‑2.0 license.

Other GGUFs of LFM2.5-1.2B-Thinking-Abliterated

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Lfm models

All Lfm →

Other tiny models

All tiny models →