HO

Holo3 35B A3B APEX

HoloGGUF by mudlerUpdated 2026-08-17
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant14.3 GB
Quick answer

Holo3 35B A3B APEX needs about 24.0 GB of memory at its main file (a 22.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 7 quants, from 14.3 GB to 25.6 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Holo3 35B A3B APEX – Vision‑Language MoE model for GUI agents

Holo3 35B A3B APEX is a 35.7B parameter vision‑language model built on the Qwen3.5‑MoE architecture. It is optimized for navigation and computer‑use agents, with 3B active parameters per token. The model supports vision and runs on the APEX quantization framework.

Good at

  • Vision‑language reasoning
  • GUI navigation
  • Multi‑step agentic tasks

Limits

  • No text‑only inference without vision
  • Requires large VRAM for full model
  • License is Apache‑2.0

Best for

  • Web and desktop automation
  • Business workflow agents
  • Complex UI interaction

Who it’s for. Developers building autonomous GUI agents or enterprise automation solutions. The model is suitable for teams needing high‑quality vision‑language reasoning in business contexts.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—14.3 GB 15.5 GB
Too big Get file →
—17.3 GB 18.5 GB
Too big Get file →
—17.3 GB 18.5 GB
Too big Get file →
—22.8 GB 24.0 GB
Too big Get file →
—22.8 GB 24.0 GB
Too big Get file →
—25.6 GB 26.8 GB
Too big Get file →
—25.6 GB 26.8 GB
Too big Get file →

For 8‑GB VRAM, the 14.32‑GB file (15.5‑GB memory at 8k context) is the smallest option. For 16‑GB VRAM, the 17.29‑GB file (18.5‑GB memory) is suitable. Larger VRAM (24‑GB+) can use the 22.82‑GB or 25.62‑GB files for higher fidelity.

What GPU do you need for Holo3 35B A3B APEX?

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: 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: the best quant that fits is the main file (14.3 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (22.8 GB file, about 24.0 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (25.6 GB file, about 26.8 GB in use).

Which Holo3 35B A3B APEX quant should you choose?

If memory is tight, the smallest file is the first one in the table at 14.3 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters34.7B (approximate, mixture of experts)
Active parameters3B
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized bymudler
FamilyHolo
Licenseapache-2.0
Downloads (HF)3,154
Last updated2026-08-17

Frequently asked questions about Holo3 35B A3B APEX

How much VRAM does Holo3 35B A3B APEX need?

About 24.0 GB at its main file with an 8K context window. That is the 22.8 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 Holo3 35B A3B APEX on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Holo3 35B A3B APEX GGUF?

It depends on the quant: file is 14.3 GB, file is 17.3 GB, file is 17.3 GB, file is 22.8 GB, file is 22.8 GB, file is 25.6 GB and 1 more.

What context length does Holo3 35B A3B APEX support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download Holo3 35B A3B APEX GGUF?

The files are on Hugging Face in the mudler/Holo3-35B-A3B-APEX-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 Holo3 35B A3B APEX 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 Holo3 35B A3B APEX on 8 GB VRAM?

No, the smallest quantized file requires at least 15.5 GB of VRAM at 8k context.

Does the model support text‑only inference?

The model includes a vision encoder; text‑only inference is not supported without the vision component.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Holo3-35B-A3B

Similar models

Browse all →

More from mudler

All by mudler →

More Holo models

All Holo →

Other large models

All large models →