HO

Holo3 35B A3B

HoloGGUF by mradermacherUpdated 2026-10-21
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant12.9 GB
Quick answer

Holo3 35B A3B needs about 22.3 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 12.9 GB (Q2_K) to 36.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Holo3 35B A3B – Vision‑Language Mixture‑of‑Experts for GUI agents

Holo3 35B A3B is a 35.7B parameter Vision‑Language Model with 3B active parameters. It is optimized for navigation and computer‑use tasks, supporting reasoning, tools, and vision. The model is released under Apache‑2.0.

Good at

  • GUI navigation
  • Multi‑step reasoning
  • Tool usage

Limits

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

Best for

  • Web browsing agents
  • Desktop automation
  • Mobile UI interaction

Who it’s for. Developers building agentic applications that need to interpret and act on graphical interfaces. The model is suitable for enterprise workflows requiring reliable multi‑step reasoning.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.9 GB 14.1 GB
Too big Get file →
Q3_K_S15.2 GB 16.4 GB
Too big Get file →
Q3_K_M16.8 GB 17.9 GB
Too big Get file →
Q3_K_L18.1 GB 19.3 GB
Too big Get file →
IQ4_XS18.9 GB 20.1 GB
Too big Get file →
Q4_K_S19.9 GB 21.1 GB
Too big Get file →
Q4_K_M21.2 GB 22.3 GB
Too big Get file →
Q5_K_S24.0 GB 25.2 GB
Too big Get file →
Q5_K_M24.7 GB 25.9 GB
Too big Get file →
Q6_K28.5 GB 29.7 GB
Too big Get file →
Q8_036.9 GB 38.1 GB
Too big Get file →

For 8‑GB VRAM use Q2_K (12.94 GB). For 12‑GB VRAM use Q3_K_S (15.18 GB). For 16‑GB VRAM use Q4_K_S (19.89 GB). Estimates are approximate and based on 8‑k context usage.

What GPU do you need for Holo3 35B A3B?

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 Q2_K (12.9 GB file, about 14.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (21.2 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.5 GB file, about 29.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (36.9 GB file, about 38.1 GB in use).

Which Holo3 35B A3B quant should you choose?

Q4_K_M is the usual starting point for Holo3 35B A3B: it balances file size and quality well. Here it is a 21.2 GB file.

The Q8_0 file is 36.9 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 12.9 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

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

Source

Quantized bymradermacher
FamilyHolo
Licenseapache-2.0
Downloads (HF)1,138
Last updated2026-10-21

Frequently asked questions about Holo3 35B A3B

How much VRAM does Holo3 35B A3B need?

About 22.3 GB at Q4_K_M with an 8K context window. That is the 21.2 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 Holo3 35B A3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.1 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: Q2_K is 12.9 GB, Q3_K_S is 15.2 GB, Q3_K_M is 16.8 GB, Q3_K_L is 18.1 GB, IQ4_XS is 18.9 GB, Q4_K_S is 19.9 GB and 5 more.

What context length does Holo3 35B A3B 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 GGUF?

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

Use the Q2_K quant, which is 12.94 GB and requires about 14.1 GB of VRAM at 8‑k context. It is the smallest quant available.

Does the model support vision in llama.cpp?

The base model has vision capabilities, but llama.cpp does not support vision for this quant set. Only text inference is supported.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing free use and modification.

Other GGUFs of Holo3-35B-A3B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Holo models

All Holo →

Other large models

All large models →