LF

LFM3 1.7B Heretic Abliterated i1

LfmGGUF by VortecksUpdated 2026-10-28
Download on Hugging Face
Parameters1.73B
Context256K
Layers24
Architecturelfm3
Smallest quant0.4 GB
Quick answer

LFM3 1.7B Heretic Abliterated i1 needs about 3.2 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 31 quants, from 0.4 GB (Q1_0) to 1.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

LFM3 1.7B Heretic Abliterated i1 – a large‑context uncensored text model

LFM3 1.7B Heretic Abliterated i1 is a 1.73B‑parameter causal language model built on Liquid AI’s tri‑hybrid architecture. It offers a 262,144‑token context window and is optimized for local agents, tool calling, and structured outputs.

Good at

  • Long‑context reasoning
  • Tool calling
  • Structured output generation

Limits

  • No vision support
  • Uncensored – lacks safety guardrails
  • Requires llama.cpp with LFM3 support

Best for

  • Local assistant agents
  • Edge deployment with long context
  • Tool‑integrated workflows

Who it’s for. Developers building local AI agents that need extended context and structured outputs. The model is suitable for users who require uncensored responses and can manage the lack of safety alignment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q1_00.4 GB 2.5 GB
Fits Get file →
IQ1_S0.5 GB 2.6 GB
Fits Get file →
IQ1_M0.5 GB 2.6 GB
Fits Get file →
TQ1_00.5 GB 2.6 GB
Fits Get file →
IQ2_XXS0.6 GB 2.7 GB
Fits Get file →
TQ2_00.6 GB 2.7 GB
Fits Get file →
IQ2_XS0.6 GB 2.7 GB
Fits Get file →
IQ2_S0.6 GB 2.7 GB
Fits Get file →
Q2_00.6 GB 2.7 GB
Fits Get file →
IQ2_M0.7 GB 2.8 GB
Fits Get file →
Q2_K_S0.7 GB 2.8 GB
Fits Get file →
IQ3_XXS0.7 GB 2.9 GB
Fits Get file →
Q2_K0.8 GB 2.9 GB
Fits Get file →
IQ3_XS0.8 GB 2.9 GB
Fits Get file →
IQ3_S0.9 GB 3.0 GB
Fits Get file →
Q3_K_S0.9 GB 3.0 GB
Fits Get file →
IQ3_M0.9 GB 3.0 GB
Fits Get file →
Q3_K_M0.9 GB 3.0 GB
Fits Get file →
Q3_K_L1.0 GB 3.1 GB
Fits Get file →
IQ4_XS1.0 GB 3.1 GB
Fits Get file →
IQ4_NL1.0 GB 3.2 GB
Fits Get file →
Q4_01.1 GB 3.2 GB
Fits Get file →
Q4_K_S1.1 GB 3.2 GB
Fits Get file →
Q4_K_M1.1 GB 3.2 GB
Fits Get file →
Q4_11.1 GB 3.3 GB
Fits Get file →
Q5_K_S1.2 GB 3.3 GB
Fits Get file →
Q5_01.2 GB 3.3 GB
Fits Get file →
Q5_K_M1.3 GB 3.4 GB
Fits Get file →
Q5_11.3 GB 3.4 GB
Fits Get file →
Q6_K1.4 GB 3.5 GB
Fits Get file →
Q8_01.8 GB 4.0 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.1 GB file, ~3.2 GB memory) or Q5_K_M (1.26 GB file, ~3.4 GB memory). For 4 GB VRAM, Q3_K_M (0.91 GB file, ~3 GB memory) is the largest that fits. Lower quants such as Q2_K (0.75 GB file, ~2.9 GB memory) reduce VRAM usage further.

What GPU do you need for LFM3 1.7B Heretic Abliterated i1?

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 Q8_0 (1.8 GB file, about 4.0 GB in use).

Which LFM3 1.7B Heretic Abliterated i1 quant should you choose?

Q4_K_M is the usual starting point for LFM3 1.7B Heretic Abliterated i1: it balances file size and quality well. Here it is a 1.1 GB file.

The Q8_0 file is 1.8 GB, about 1.7 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 Q1_0 at 0.4 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm3
Parameters1.73B
Layers24
Trained context262,144 tokens
KV cache (fp16)192 KB per token

Source

Quantized byVortecks
FamilyLfm
Licenseother
Downloads (HF)4,897
Last updated2026-10-28

Frequently asked questions about LFM3 1.7B Heretic Abliterated i1

How much VRAM does LFM3 1.7B Heretic Abliterated i1 need?

About 3.2 GB at Q4_K_M with an 8K context window. That is the 1.1 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 LFM3 1.7B Heretic Abliterated i1 on an 8 GB GPU?

Yes, with Q8_0: the 1.8 GB file needs about 4.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LFM3 1.7B Heretic Abliterated i1 GGUF?

It depends on the quant: Q1_0 is 0.4 GB, IQ1_S is 0.5 GB, IQ1_M is 0.5 GB, TQ1_0 is 0.5 GB, IQ2_XXS is 0.6 GB, TQ2_0 is 0.6 GB and 25 more.

What context length does LFM3 1.7B Heretic Abliterated i1 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download LFM3 1.7B Heretic Abliterated i1 GGUF?

The files are on Hugging Face in the Vortecks/LFM3-1.7B-Heretic-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 LFM3 1.7B Heretic Abliterated i1 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 LFM3 1.7B on 8 GB VRAM?

Yes. The Q4_K_M quant uses about 3.2 GB of VRAM at 8 k context, which fits within 8 GB.

Does this model support image input?

No. The model is a text‑only causal language model.

What is the context length of this model?

The model supports a 262,144‑token context window.

Other GGUFs of LFM3-1.7B-Heretic-Abliterated

Similar models

Browse all →

More from Vortecks

All by Vortecks →

More Lfm models

All Lfm →

Other tiny models

All tiny models →