SU

Sulphur 2 distilled Q4 K M

SulphurGGUF by coolthorUpdated 2026-07-22
Download on Hugging Face
Parameters21B
Context—
Layers—
Architectureltxv
Smallest quant14.2 GB
Quick answer

Sulphur 2 distilled Q4 K M needs about 16.4 GB of memory at Q4_K_M (a 14.2 GB file) with an 8K context window, so it fits on a 24 GB GPU.

Sulphur 2 distilled Q4_K_M – 21B LTX video generation model

Sulphur 2 distilled Q4_K_M is a 21B parameter LTX video generation model. It supports t2v and i2v natively and includes BF16 text/audio auxiliary components. The model is distributed as a GGUF file for ComfyUI and llama.cpp.

Good at

  • Video generation with audio
  • Low‑precision inference on older GPUs
  • ComfyUI integration

Limits

  • Requires ~16.4 GB VRAM at 8k context
  • No official inference yet
  • License is other, not open source

Best for

  • Generating short video clips
  • Audio‑visual content creation
  • Testing LTX video workflows

Who it’s for. Developers and researchers needing a lightweight video generation model for older NVIDIA GPUs. The model is useful for those who want to experiment with LTX video VAE and audio sampling without high‑end hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M14.2 GB 16.4 GB
Too big Get file →

The only available quant is Q4_K_M, with a file size of 14.19 GB and an estimated VRAM usage of 16.4 GB at 8k context. This is the recommended quant for systems with 16 GB or more VRAM. For lower budgets, no other quant is provided.

What GPU do you need for Sulphur 2 distilled Q4 K M?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_K_M (14.2 GB file, about 16.4 GB in use).

Which Sulphur 2 distilled Q4 K M quant should you choose?

Q4_K_M is the usual starting point for Sulphur 2 distilled Q4 K M: it balances file size and quality well. Here it is a 14.2 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureltxv
Parameters21B

Source

Quantized bycoolthor
FamilySulphur
Licenseother
Downloads (HF)3,616
Last updated2026-07-22

Frequently asked questions about Sulphur 2 distilled Q4 K M

How much VRAM does Sulphur 2 distilled Q4 K M need?

About 16.4 GB at Q4_K_M with an 8K context window. That is the 14.2 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 Sulphur 2 distilled Q4 K M on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Sulphur 2 distilled Q4 K M GGUF?

It depends on the quant: Q4_K_M is 14.2 GB.

Where can I download Sulphur 2 distilled Q4 K M GGUF?

The files are on Hugging Face in the coolthor/Sulphur-2-distilled-Q4_K_M-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 Sulphur 2 distilled Q4 K M 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 Sulphur 2 distilled on 8 GB VRAM?

No. The model requires approximately 16.4 GB VRAM at 8k context.

Does the model support text‑only generation?

No. Sulphur 2 distilled is a video generation model with audio support.

What license does the model use?

The model is released under an other license; it is not open source.

Other GGUFs of Sulphur-2-base

Similar models

Browse all →

More from coolthor

All by coolthor →

More Sulphur models

All Sulphur →

Other medium models

All medium models →