Holo 3.1 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.
Holo 3.1 35B A3B – Vision‑Language model for local computer use agents
Holo 3.1 35B A3B is a 34.7B parameter Vision‑Language model built on the qwen35moe architecture. It supports reasoning, tools, and vision tasks and is optimized for local deployment via GGUF quantizations. The model is released under the Apache‑2.0 license.
Good at
- Vision‑language reasoning
- Computer use agent tasks
- Mobile automation
Limits
- Requires large VRAM for full precision
- No native vision support in lower‑rank quants
- Limited to text‑based contexts
Best for
- Local UI automation scripts
- Mobile app testing agents
- Enterprise workflow assistants
Who it’s for. Developers and researchers needing a high‑capacity vision‑language model that can run locally. The model is suitable for building agents that interact with desktop, web, and mobile interfaces.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 12.9 GB | 14.1 GB | Too big | Get file → | |
| Q3_K_S | 15.2 GB | 16.4 GB | Too big | Get file → | |
| Q3_K_M | 16.8 GB | 17.9 GB | Too big | Get file → | |
| Q3_K_L | 18.1 GB | 19.3 GB | Too big | Get file → | |
| IQ4_XS | 18.9 GB | 20.1 GB | Too big | Get file → | |
| Q4_K_S | 19.9 GB | 21.1 GB | Too big | Get file → | |
| Q4_K_M | 21.2 GB | 22.3 GB | Too big | Get file → | |
| Q5_K_S | 24.0 GB | 25.2 GB | Too big | Get file → | |
| Q5_K_M | 24.7 GB | 25.9 GB | Too big | Get file → | |
| Q6_K | 28.5 GB | 29.7 GB | Too big | Get file → | |
| Q8_0 | 36.9 GB | 38.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_S (file size 19.89 GB, estimated 21.1 GB memory). For 12 GB VRAM, Q5_K_S (23.98 GB, 25.2 GB memory) is a good balance. If memory is limited to 6 GB, Q2_K (12.94 GB, 14.1 GB memory) is the only viable option, though performance will be reduced.
What GPU do you need for Holo 3.1 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 Holo 3.1 35B A3B quant should you choose?
Q4_K_M is the usual starting point for Holo 3.1 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
Source
Frequently asked questions about Holo 3.1 35B A3B
How much VRAM does Holo 3.1 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 Holo 3.1 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 Holo 3.1 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 Holo 3.1 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 Holo 3.1 35B A3B GGUF?
The files are on Hugging Face in the mradermacher/Holo-3.1-35B-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 Holo 3.1 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 Holo 3.1 35B A3B on 8 GB VRAM?
Yes, using the Q4_K_S quantization. It requires approximately 21.1 GB of VRAM at 8k context, so you would need a higher‑capacity GPU or batch size reduction.
Does the model support vision tasks?
Yes, the model includes vision capabilities as part of its detected abilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.