LL

LLaDa Image Turbo ComfyUI

LladaGGUF by realrebelaiUpdated 2026-09-04
Download on Hugging Face
Parameters16.3B
Context—
Layers—
Architecturelumina2
Smallest quant9.2 GB
Quick answer

LLaDa Image Turbo ComfyUI needs about 10.8 GB of memory at Q4_K_M (a 9.2 GB file) with an 8K context window, so it fits on a 12 GB GPU.

LLaDa Image Turbo ComfyUI – fast 4‑step image generation and editing

LLaDa Image Turbo is a 16.3‑billion‑parameter model optimized for quick text‑to‑image generation and native image editing. It is a distilled version of LLaDA‑Image, delivering high‑quality images in only 4 sampling steps. The model is available as a Q4_K_M GGUF file for efficient inference.

Good at

  • Fast 4‑step image generation
  • Native image editing without separate backbone
  • High‑quality photorealistic outputs

Limits

  • Requires 10.8 GB VRAM at 8 k context
  • No vision support beyond image generation
  • No license information provided

Best for

  • Rapid prototyping of image prompts
  • Low‑latency image editing workflows
  • ComfyUI integration for quick demos

Who it’s for. Developers and artists seeking a lightweight, fast image generation model for ComfyUI. It is suitable for users who need quick iterations and native editing without additional checkpoints.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M9.2 GB 10.8 GB
Too big Get file →

The only available quantization is Q4_K_M, 9.18 GB in size. It needs roughly 10.8 GB VRAM at 8 k context, so a system with at least 16 GB VRAM is recommended. For lower VRAM budgets, a higher‑quantized version would be required, but none is provided here.

What GPU do you need for LLaDa Image Turbo ComfyUI?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q4_K_M (9.2 GB file, about 10.8 GB in use).

Which LLaDa Image Turbo ComfyUI quant should you choose?

Q4_K_M is the usual starting point for LLaDa Image Turbo ComfyUI: it balances file size and quality well. Here it is a 9.2 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelumina2
Parameters16.3B

Source

Quantized byrealrebelai
FamilyLlada
Downloads (HF)5,535
Last updated2026-09-04

Frequently asked questions about LLaDa Image Turbo ComfyUI

How much VRAM does LLaDa Image Turbo ComfyUI need?

About 10.8 GB at Q4_K_M with an 8K context window. That is the 9.2 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 LLaDa Image Turbo ComfyUI on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of LLaDa Image Turbo ComfyUI GGUF?

It depends on the quant: Q4_K_M is 9.2 GB.

Where can I download LLaDa Image Turbo ComfyUI GGUF?

The files are on Hugging Face in the realrebelai/LLaDa-Image-Turbo_ComfyUI repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run LLaDa Image Turbo on 8 GB VRAM?

The Q4_K_M quantization requires about 10.8 GB VRAM at 8 k context, so 8 GB is insufficient.

Does the model support multiple languages?

No language support is listed; the model is primarily for image generation and editing.

Is native image editing supported?

Yes, the model supports native image editing via the generation_mode="editing" setting in ComfyUI.

Other GGUFs of LLaDA-Image-Turbo

Similar models

Browse all →

More from realrebelai

All by realrebelai →

More Llada models

All Llada →

Other medium models

All medium models →