HU

humo

HumoGGUF by calcuisUpdated 2025-09-18
Download on Hugging Face
Parameters1.74B
Context—
Layers—
Architecturepig
Smallest quant0.7 GB
Quick answer

humo needs about 1.9 GB of memory at Q4_K_M (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 23 quants, from 0.7 GB (Q2_K) to 18.9 GB (Q8_0).

HuMo 1.7B video generation model in GGUF format

HuMo is a 1.7B parameter model for human‑centric video generation. It supports text, image, and audio multimodal inputs. The model is released under the apache‑2.0 license.

Good at

  • Multimodal video generation
  • Text‑image conditioning
  • Audio‑driven motion

Limits

  • No vision support in llama.cpp
  • Requires 8k context for estimates
  • Large memory for higher quants

Best for

  • Creative video production
  • Audio‑sync video creation
  • Text‑image‑audio storytelling

Who it’s for. Developers and researchers building multimodal video generation pipelines. The model is suitable for users who need fine‑grained control over human video output and can run inference on GPUs with sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.7 GB 1.3 GB
Fits Get file →
Q3_K_S0.9 GB 1.5 GB
Fits Get file →
Q3_K_M0.9 GB 1.5 GB
Fits Get file →
Q3_K_L1.0 GB 1.6 GB
Fits Get file →
IQ4_XS1.0 GB 1.6 GB
Fits Get file →
IQ4_NL1.1 GB 1.7 GB
Fits Get file →
Q4_01.1 GB 1.7 GB
Fits Get file →
Q4_K_S1.1 GB 1.8 GB
Fits Get file →
Q4_11.2 GB 1.8 GB
Fits Get file →
Q4_K_M1.2 GB 1.9 GB
Fits Get file →
Q5_K_S1.3 GB 1.9 GB
Fits Get file →
Q5_01.3 GB 2.0 GB
Fits Get file →
Q5_K_M1.4 GB 2.0 GB
Fits Get file →
Q5_11.4 GB 2.1 GB
Fits Get file →
Q6_K1.5 GB 2.2 GB
Fits Get file →
Q8_01.9 GB 2.6 GB
Fits Get file →
Q3_K_S8.3 GB 9.8 GB
Too big Get file →
IQ4_XS10.0 GB 11.7 GB
Too big Get file →
IQ4_NL10.6 GB 12.3 GB
Too big Get file →
Q4_010.7 GB 12.5 GB
Too big Get file →
Q5_012.8 GB 14.9 GB
Too big Get file →
Q6_K14.9 GB 17.2 GB
Too big Get file →
Q8_018.9 GB 21.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 1.13 GB, estimated 1.8 GB memory). For 16 GB VRAM, Q5_K_M (1.37 GB, 2 GB memory) or Q6_K (1.51 GB, 2.2 GB memory). For 32 GB VRAM, Q8_0 (1.91 GB, 2.6 GB memory) provides higher quality.

What GPU do you need for humo?

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 Q8_0 (1.9 GB file, about 2.6 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (1.9 GB file, about 2.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (1.9 GB file, about 2.6 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ4_XS (10.0 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_0 (12.8 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (18.9 GB file, about 21.7 GB in use).

Which humo quant should you choose?

Q4_K_M is the usual starting point for humo: it balances file size and quality well. Here it is a 1.2 GB file.

The Q8_0 file is 1.9 GB, about 1.5 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 0.7 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

Architecturepig
Parameters1.74B

Source

Quantized bycalcuis
FamilyHumo
Licenseapache-2.0
Downloads (HF)739
Last updated2025-09-18

Frequently asked questions about humo

How much VRAM does humo need?

About 1.9 GB at Q4_K_M with an 8K context window. That is the 1.2 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 humo on an 8 GB GPU?

Yes, with Q8_0: the 1.9 GB file needs about 2.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of humo GGUF?

It depends on the quant: Q2_K is 0.7 GB, Q3_K_S is 0.9 GB, Q3_K_M is 0.9 GB, Q3_K_L is 1.0 GB, IQ4_XS is 1.0 GB, IQ4_NL is 1.1 GB and 17 more.

Where can I download humo GGUF?

The files are on Hugging Face in the calcuis/humo-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 humo 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 HuMo on 8 GB VRAM?

Yes, using the Q4_K_S quantization which requires about 1.8 GB memory at 8k context.

Does HuMo support vision inputs in llama.cpp?

No, the model does not include vision support in llama.cpp.

Other GGUFs of HuMo

Similar models

Browse all →

More from calcuis

All by calcuis →

More Humo models

All Humo →

Other tiny models

All tiny models →