Holo4 35B A3B GSQ RCO needs about 14.3 GB of memory at IQ3_XXS (a 13.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 13.1 GB (IQ3_XXS) to 15.2 GB (IQ3_S). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
Holo4 35B A3B GSQ RCO – a vision‑language Mixture‑of‑Experts model
Holo4 35B A3B GSQ RCO is a 34.7 billion‑parameter vision‑language model built on Qwen3.6‑35B‑A3B. It supports reasoning, tools, and vision tasks and is optimized for llama.cpp via per‑tensor mixed‑precision GGUF builds. The model offers a 262,144‑token context window.
Good at
- Vision‑language reasoning
- Tool‑based computer use
- Large context handling
Limits
- No MTP block
- Requires 8k context for memory estimates
- License is Apache‑2.0
Best for
- Automated GUI interaction
- Complex document analysis
- Long‑form visual content generation
Who it’s for. Developers building AI agents that need to interpret images, execute tools, and maintain long conversations. The model is suitable for applications that can handle the memory demands of a 35B Mixture‑of‑Experts architecture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XXS | 13.1 GB | 14.3 GB | Too big | Get file → | |
| IQ3_S | 15.2 GB | 16.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ3_XXS (13.07 GB file, ~14.3 GB memory at 8k context). For 12 GB VRAM, IQ3_S (15.23 GB file, ~16.4 GB memory at 8k context) provides higher quality. Memory estimates are approximate.
What GPU do you need for Holo4 35B A3B GSQ RCO?
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 IQ3_XXS (13.1 GB file, about 14.3 GB in use).
- 24 GB VRAM: the best quant that fits is IQ3_S (15.2 GB file, about 16.4 GB in use).
Which Holo4 35B A3B GSQ RCO quant should you choose?
IQ3_XXS (13.1 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Holo4 35B A3B GSQ RCO
How much VRAM does Holo4 35B A3B GSQ RCO need?
About 14.3 GB at IQ3_XXS with an 8K context window. That is the 13.1 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 Holo4 35B A3B GSQ RCO on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Holo4 35B A3B GSQ RCO GGUF?
It depends on the quant: IQ3_XXS is 13.1 GB, IQ3_S is 15.2 GB.
What context length does Holo4 35B A3B GSQ RCO 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 2.8 GB at 32K.
Where can I download Holo4 35B A3B GSQ RCO GGUF?
The files are on Hugging Face in the lavendercomputing/Holo4-35B-A3B-GSQ-RCO-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 Holo4 35B A3B GSQ RCO 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 this model on 8 GB VRAM?
Yes, using the IQ3_XXS quantized build which requires about 14.3 GB of VRAM at 8k context.
Does the model support vision tasks?
Yes, it includes a BF16 mmproj for vision and is designed for vision‑language use.
What license applies to this model?
The model is released under the Apache‑2.0 license.