LF

LFM3 1.7B Base heretic

LfmGGUF by saidutta69Updated 2026-10-28
Download on Hugging Face
Parameters1.73B
Context256K
Layers24
Architecturelfm3
Smallest quant0.8 GB
Quick answer

LFM3 1.7B Base heretic 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 15 quants, from 0.8 GB (Q2_K) to 3.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

LFM3 1.7B Base heretic – a decensored, fine‑tuning ready LLM

LFM3 1.7B Base heretic is a 1.73B parameter model based on the Lfm3 architecture. It supports 262144 context tokens and is designed for heavy fine‑tuning. The model is decensored and removes refusal behavior before alignment training.

Good at

  • Coding
  • Reasoning
  • Tool usage

Limits

  • No built‑in chat persona
  • No vision or audio support
  • Requires heavy fine‑tuning for best use

Best for

  • Custom domain assistants
  • Proprietary data training
  • Post‑training experiments

Who it’s for. Developers who want a base model with refusal direction removed before SFT/DPO/GRPO. It is not a ready‑to‑use chat or agent model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.8 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 →
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 →
Q4_01.0 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_K_M1.3 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 →
F163.5 GB 5.6 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 1.1 GB, estimated 3.2 GB memory). For 4 GB VRAM, use Q2_K (0.75 GB, 2.9 GB memory). For 2 GB VRAM, use IQ3_S (0.85 GB, 3 GB memory).

What GPU do you need for LFM3 1.7B Base heretic?

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).
  • 6 GB VRAM: the best quant that fits is F16 (3.5 GB file, about 5.6 GB in use).

Which LFM3 1.7B Base heretic quant should you choose?

Q4_K_M is the usual starting point for LFM3 1.7B Base heretic: 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 Q2_K at 0.8 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

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

Source

Quantized bysaidutta69
FamilyLfm
Licenseother
Downloads (HF)1,373
Last updated2026-10-28

Frequently asked questions about LFM3 1.7B Base heretic

How much VRAM does LFM3 1.7B Base heretic 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 Base heretic on an 8 GB GPU?

Yes, with F16: the 3.5 GB file needs about 5.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LFM3 1.7B Base heretic GGUF?

It depends on the quant: Q2_K is 0.8 GB, IQ3_S is 0.9 GB, Q3_K_S is 0.9 GB, Q3_K_M is 0.9 GB, Q3_K_L is 1.0 GB, IQ4_XS is 1.0 GB and 9 more.

What context length does LFM3 1.7B Base heretic 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 Base heretic GGUF?

The files are on Hugging Face in the saidutta69/LFM3-1.7B-Base-heretic 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 Base heretic 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 Base heretic on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 3.2 GB memory at 8 k context, fitting within 8 GB VRAM.

Does this model support vision or audio?

No, it is a text‑only base model with no vision or audio capabilities.

What is the context length of this model?

The model supports 262144 tokens of context length.

Other GGUFs of LFM3-1.7B-Base

Similar models

Browse all →

More from saidutta69

All by saidutta69 →

More Lfm models

All Lfm →

Other tiny models

All tiny models →