LF

LFM3 VL 2B Heretic

LfmGGUF by HydroLabsUpdated 2026-10-29
Download on Hugging Face
Parameters1.73B
Context125K
Layers24
Architecturelfm3
Smallest quant1.5 GB
Quick answer

LFM3 VL 2B Heretic needs about 3.6 GB of memory at Q6_K (a 1.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.5 GB (Q6_K) to 3.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

LFM3 VL 2B Heretic – vision‑language model with reasoning

LFM3 VL 2B Heretic is a 1.73B parameter model that combines a language model with a vision encoder. It supports text, image, and video input and reasons step by step before answering. The model is available in GGUF format quantized by HydroLabs.

Good at

  • Vision‑language reasoning
  • Video understanding
  • Spatial and embodied reasoning

Limits

  • Requires at least 8K context tokens
  • Memory usage depends on quantization
  • License is other

Best for

  • On‑device visual question answering
  • Video analysis for education
  • Robotics visual planning

Who it’s for. Developers building on‑device vision‑language applications who need reasoning capabilities and can manage the memory requirements. The model is suitable for edge devices with sufficient VRAM and RAM to load the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K1.5 GB 3.6 GB
Fits Get file →
BF163.5 GB 5.6 GB
Fits Get file →

For 8GB VRAM, use Q6_K (1.49GB file, ~3.6GB memory at 8K context). For higher memory budgets, BF16 (3.47GB file, ~5.6GB memory at 8K context) offers higher precision. Choose the quant that fits your VRAM and RAM constraints.

What GPU do you need for LFM3 VL 2B 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 Q6_K (1.5 GB file, about 3.6 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (3.5 GB file, about 5.6 GB in use).

Which LFM3 VL 2B Heretic quant should you choose?

Q6_K (1.5 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm3
Parameters1.73B
Layers24
Trained context128,000 tokens
KV cache (fp16)192 KB per token

Source

Quantized byHydroLabs
FamilyLfm
Licenseother
Downloads (HF)834
Last updated2026-10-29

Frequently asked questions about LFM3 VL 2B Heretic

How much VRAM does LFM3 VL 2B Heretic need?

About 3.6 GB at Q6_K with an 8K context window. That is the 1.5 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 LFM3 VL 2B Heretic on an 8 GB GPU?

Yes, with BF16: 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 VL 2B Heretic GGUF?

It depends on the quant: Q6_K is 1.5 GB, BF16 is 3.5 GB.

What context length does LFM3 VL 2B Heretic support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download LFM3 VL 2B Heretic GGUF?

The files are on Hugging Face in the HydroLabs/LFM3-VL-2B-Heretic-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 VL 2B 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 VL 2B Heretic on 8 GB VRAM?

Yes, the Q6_K quantization requires about 3.6GB memory at 8K context, which fits within 8GB VRAM.

What context length does the model support?

The model supports 128K tokens of context, but at least 8K tokens are recommended for reliable reasoning.

Does the model support vision input?

Yes, it accepts images and video at native resolution and processes them with a 14‑layer vision encoder.

Other GGUFs of LFM3-VL-2B

Similar models

Browse all →

More Lfm models

All Lfm →

Other tiny models

All tiny models →