LO

LongCat Image Edit

LongcatGGUF by vantagewithaiUpdated 2026-03-24
Download on Hugging Face
Parameters6.29B
Context—
Layers—
Architectureflux
Smallest quant2.8 GB
Quick answer

LongCat Image Edit needs about 4.8 GB of memory at Q4_K_M (a 3.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 13 quants, from 2.8 GB (Q2_K) to 6.7 GB (Q8_0).

LongCat Image Edit – bilingual image editing with strong consistency

LongCat Image Edit is a 6.29B parameter flux model for image editing. It supports bilingual Chinese‑English instructions and offers precise global, local, text, and reference‑guided editing. The model is licensed under apache‑2.0.

Good at

  • Precise global and local editing
  • Strong consistency preservation
  • Bilingual instruction support

Limits

  • No vision support beyond image editing
  • Requires 8k context for memory estimates
  • Large memory needs for higher quants

Best for

  • Image retouching
  • Text‑based image modification
  • Reference‑guided edits

Who it’s for. Developers and researchers needing a bilingual, high‑quality image editing model. Suitable for integration into ComfyUI workflows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.8 GB 3.6 GB
Fits Get file →
Q3_K_S3.2 GB 4.1 GB
Fits Get file →
Q3_K_M3.3 GB 4.2 GB
Fits Get file →
Q4_03.8 GB 4.8 GB
Fits Get file →
Q4_K_S3.8 GB 4.8 GB
Fits Get file →
Q4_K_M3.9 GB 4.8 GB
Fits Get file →
Q4_14.1 GB 5.1 GB
Fits Get file →
Q5_04.4 GB 5.4 GB
Fits Get file →
Q5_K_S4.4 GB 5.4 GB
Fits Get file →
Q5_14.7 GB 5.7 GB
Fits Get file →
Q5_K_M4.7 GB 5.7 GB
Fits Get file →
Q6_K5.2 GB 6.3 GB
Fits Get file →
Q8_06.7 GB 8.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 or Q4_K_S (≈4.8 GB memory). For 6 GB VRAM, Q3_K_M (≈4.2 GB). For 4 GB VRAM, Q2_K (≈3.6 GB). Estimates are approximate.

What GPU do you need for LongCat Image Edit?

These figures add the file size, an fp16 KV cache at an 8K context window 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 Q2_K (2.8 GB file, about 3.6 GB in use).
  • 6 GB VRAM: the best quant that fits is Q5_K_M (4.7 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (6.7 GB file, about 8.0 GB in use).

Which LongCat Image Edit quant should you choose?

Q4_K_M is the usual starting point for LongCat Image Edit: it balances file size and quality well. Here it is a 3.9 GB file.

The Q8_0 file is 6.7 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 2.8 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

Architectureflux
Parameters6.29B

Source

Quantized byvantagewithai
FamilyLongcat
Licenseapache-2.0
Downloads (HF)4,527
Last updated2026-03-24

Frequently asked questions about LongCat Image Edit

How much VRAM does LongCat Image Edit need?

About 4.8 GB at Q4_K_M with an 8K context window. That is the 3.9 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 LongCat Image Edit on an 8 GB GPU?

Yes, with Q8_0: the 6.7 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LongCat Image Edit GGUF?

It depends on the quant: Q2_K is 2.8 GB, Q3_K_S is 3.2 GB, Q3_K_M is 3.3 GB, Q4_0 is 3.8 GB, Q4_K_S is 3.8 GB, Q4_K_M is 3.9 GB and 7 more.

Where can I download LongCat Image Edit GGUF?

The files are on Hugging Face in the vantagewithai/LongCat-Image-Edit-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 LongCat Image Edit use?

Hugging Face lists the license as apache-2.0. 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 LongCat Image Edit on 8 GB VRAM?

Yes, using Q4_0 or Q4_K_S quantization which requires about 4.8 GB of VRAM at 8k context.

Does the model support multilingual instructions?

It supports bilingual Chinese‑English editing instructions.

Similar models

Browse all →

More from vantagewithai

All by vantagewithai →

More Longcat models

All Longcat →

Other small models

All small models →