LF

LFM3 VL 2B Surgical Abliterated

LfmGGUF by medismeraUpdated 2026-10-30
Download on Hugging Face
Parameters1.73B
Context125K
Layers24
Architecturelfm3
Smallest quant1.1 GB
Quick answer

LFM3 VL 2B Surgical Abliterated 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. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

LFM3 VL 2B Surgical Abliterated – 1.73B vision‑language model

LFM3 VL 2B Surgical Abliterated is a 1.73B parameter vision‑language model. It accepts text, images, and video and reasons step by step. The model is a surgical ablation of the refusal subspace, providing neutral responses.

Good at

  • Vision‑language reasoning
  • Video understanding
  • Multi‑step reasoning

Limits

  • No vision support beyond images and video
  • Large VRAM requirement
  • License is other

Best for

  • On‑device visual QA
  • Video lecture analysis
  • Robotics visual reasoning

Who it’s for. Developers needing a compact vision‑language model for on‑device inference. Researchers working on multimodal reasoning tasks who prefer open‑source models.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.1 GB 3.2 GB
Fits Get file →

The Q4_K_M quant is 1.1 GB and requires about 3.2 GB of VRAM at 8 k context. It is suitable for systems with 8 GB or more VRAM. For tighter budgets, a higher‑quantization model would be needed, but none are available in the file list.

What GPU do you need for LFM3 VL 2B Surgical 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 Q4_K_M (1.1 GB file, about 3.2 GB in use).

Which LFM3 VL 2B Surgical Abliterated quant should you choose?

Q4_K_M is the usual starting point for LFM3 VL 2B Surgical Abliterated: it balances file size and quality well. Here it is a 1.1 GB file.

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 bymedismera
FamilyLfm
Licenseother
Downloads (HF)710
Last updated2026-10-30

Frequently asked questions about LFM3 VL 2B Surgical Abliterated

How much VRAM does LFM3 VL 2B Surgical Abliterated 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 VL 2B Surgical Abliterated on an 8 GB GPU?

Yes, with Q4_K_M: the 1.1 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LFM3 VL 2B Surgical Abliterated GGUF?

It depends on the quant: Q4_K_M is 1.1 GB.

What context length does LFM3 VL 2B Surgical 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 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download LFM3 VL 2B Surgical Abliterated GGUF?

The files are on Hugging Face in the medismera/LFM3-VL-2B-Surgical-Abliterated 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 Surgical Abliterated 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, the Q4_K_M quant uses about 3.2 GB of VRAM at 8 k context, leaving headroom for other processes.

Does the model support multiple languages?

Yes, it supports English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish, Vietnamese, Thai, Indonesian, Hindi, Russian, and Polish.

What is the context length of this model?

The model supports 128 000 tokens of context, including input and output.

Other GGUFs of LFM3-VL-2B

Similar models

Browse all →

More from medismera

All by medismera →

More Lfm models

All Lfm →

Other tiny models

All tiny models →