LF

Lfm2.5-Vl-1.6B

LfmGGUF by unslothUpdated 2026-08-05
Download on Hugging Face
Parameters1.17B
Context125K
Layers16
Architecturelfm2
Smallest quant0.5 GB
Quick answer

Lfm2.5-Vl-1.6B 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 19 quants, from 0.5 GB (Q2_K) to 2.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

LFM2.5‑VL‑1.6B – a 1.17B‑parameter vision‑language model

LFM2.5‑VL‑1.6B is a general‑purpose vision‑language model with a 32,768‑token context length. It uses the SigLIP2 NaFlex vision encoder and supports multilingual vision tasks in English, Arabic, Chinese, French, German, Japanese, Korean, and Spanish.

Good at

  • Multilingual vision understanding
  • OCR and document comprehension
  • Real‑time video captioning

Limits

  • No knowledge‑intensive tasks
  • Requires 8,000‑token context for memory estimates
  • License is other

Best for

  • Vision‑language inference on local GPUs
  • OCR pipelines
  • Real‑time video captioning demos

Who it’s for. Developers building vision‑language applications that need multilingual support and robust image understanding. Suitable for local inference with llama.cpp or Hugging Face transformers.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.5 GB 2.1 GB
Fits Get file →
Q2_K_L0.5 GB 2.1 GB
Fits Get file →
Q2_K_XL0.5 GB 2.1 GB
Fits Get file →
Q3_K_S0.6 GB 2.1 GB
Fits Get file →
Q3_K_M0.6 GB 2.2 GB
Fits Get file →
Q3_K_XL0.6 GB 2.2 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_K_XL0.7 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 →
Q5_K_XL0.8 GB 2.4 GB
Fits Get file →
Q6_K1.0 GB 2.5 GB
Fits Get file →
Q6_K_XL1.0 GB 2.6 GB
Fits Get file →
Q8_01.2 GB 2.8 GB
Fits Get file →
Q8_K_XL1.4 GB 2.9 GB
Fits Get file →
BF162.3 GB 3.9 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 0.73 GB, estimated 2.3 GB memory). For 12 GB VRAM, Q5_K_M (0.84 GB, 2.4 GB memory) offers a balance of quality and size. For higher precision, BF16 (2.34 GB, 3.9 GB memory) is available but requires more VRAM.

What GPU do you need for Lfm2.5-Vl-1.6B?

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 BF16 (2.3 GB file, about 3.9 GB in use).

Which Lfm2.5-Vl-1.6B quant should you choose?

Q4_K_M is the usual starting point for Lfm2.5-Vl-1.6B: it balances file size and quality well. Here it is a 0.7 GB file.

The Q8_0 file is 1.2 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 0.5 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

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

Source

Quantized byunsloth
FamilyLfm
Licenseother
Downloads (HF)2,274
Last updated2026-08-05

Frequently asked questions about Lfm2.5-Vl-1.6B

How much VRAM does Lfm2.5-Vl-1.6B 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-Vl-1.6B on an 8 GB GPU?

Yes, with BF16: the 2.3 GB file needs about 3.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Lfm2.5-Vl-1.6B GGUF?

It depends on the quant: Q2_K is 0.5 GB, Q2_K_L is 0.5 GB, Q2_K_XL is 0.5 GB, Q3_K_S is 0.6 GB, Q3_K_M is 0.6 GB, Q3_K_XL is 0.6 GB and 13 more.

What context length does Lfm2.5-Vl-1.6B 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-Vl-1.6B GGUF?

The files are on Hugging Face in the unsloth/LFM2.5-VL-1.6B-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-Vl-1.6B 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 LFM2.5‑VL‑1.6B on 8 GB VRAM?

Yes, using a Q4_K_M quantized file will fit within 8 GB VRAM with an estimated 2.3 GB memory usage at 8,000 tokens.

Does the model support image inputs larger than 512×512?

The model natively processes images up to 512×512 pixels. Larger images are tiled into 512×512 patches for processing.

Is there a chat template for llama.cpp?

Yes, the model includes Unsloth chat template fixes. Use the --jinja flag when running with llama.cpp.

Other GGUFs of LFM2.5-VL-1.6B

Similar models

Browse all →

More from unsloth

All by unsloth →

More Lfm models

All Lfm →

Other tiny models

All tiny models →