Holo 3.1 4B needs about 4.6 GB of memory at Q4_K_M (a 3.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 4.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Holo 3.1 4B – a 4.84B parameter vision‑language model for local computer use agents
Holo 3.1 4B is a 4.84B parameter model built on the Qwen 3.5 architecture. It supports reasoning and tool usage for computer use tasks. The model is released under the Apache 2.0 license and is available in multiple GGUF quantizations.
Good at
- Reasoning tasks
- Tool invocation
- Computer use automation
Limits
- No vision support in the provided GGUF files
- Large context requires significant VRAM
- Requires 8‑k context for memory estimates
Best for
- Local agent development
- Desktop automation scripts
- Mobile UI automation
Who it’s for. Developers building local computer use agents who need a lightweight vision‑language model. The model is suitable for environments where local inference is preferred and the Apache 2.0 license is acceptable.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| IQ1_S | 1.6 GB | 3.1 GB | Fits | Get file → | |
| IQ1_M | 1.6 GB | 3.2 GB | Fits | Get file → | |
| IQ2_XXS | 1.7 GB | 3.3 GB | Fits | Get file → | |
| IQ2_XS | 1.8 GB | 3.4 GB | Fits | Get file → | |
| IQ2_S | 1.9 GB | 3.5 GB | Fits | Get file → | |
| IQ2_M | 2.0 GB | 3.6 GB | Fits | Get file → | |
| Q2_K_S | 2.1 GB | 3.6 GB | Fits | Get file → | |
| Q2_K | 2.1 GB | 3.7 GB | Fits | Get file → | |
| IQ3_XXS | 2.2 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_S | 2.3 GB | 3.9 GB | Fits | Get file → | |
| IQ3_XS | 2.4 GB | 3.9 GB | Fits | Get file → | |
| IQ3_S | 2.4 GB | 4.0 GB | Fits | Get file → | |
| IQ3_M | 2.4 GB | 4.0 GB | Fits | Get file → | |
| Q3_K_M | 2.5 GB | 4.1 GB | Fits | Get file → | |
| Q3_K_L | 2.7 GB | 4.3 GB | Fits | Get file → | |
| IQ4_XS | 2.9 GB | 4.4 GB | Fits | Get file → | |
| Q4_0 | 2.9 GB | 4.5 GB | Fits | Get file → | |
| Q4_K_S | 2.9 GB | 4.5 GB | Fits | Get file → | |
| IQ4_NL | 3.0 GB | 4.5 GB | Fits | Get file → | |
| Q4_K_M | 3.1 GB | 4.6 GB | Fits | Get file → | |
| Q4_1 | 3.2 GB | 4.7 GB | Fits | Get file → | |
| Q5_K_S | 3.4 GB | 5.0 GB | Fits | Get file → | |
| Q5_K_M | 3.5 GB | 5.1 GB | Fits | Get file → | |
| Q6_K | 4.0 GB | 5.6 GB | Fits | Get file → |
For 8‑GB VRAM, the Q4_K_M quant (3.07 GB file, 4.6 GB memory at 8‑k context) is a good balance. If more VRAM is available, Q5_K_M (3.51 GB, 5.1 GB memory) offers higher fidelity. For the tightest memory budget, IQ1_S (1.57 GB, 3.1 GB memory) is recommended.
What GPU do you need for Holo 3.1 4B?
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: the best quant that fits is IQ3_M (2.4 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (4.0 GB file, about 5.6 GB in use).
Which Holo 3.1 4B quant should you choose?
Q4_K_M is the usual starting point for Holo 3.1 4B: it balances file size and quality well. Here it is a 3.1 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 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
Source
Frequently asked questions about Holo 3.1 4B
How much VRAM does Holo 3.1 4B need?
About 4.6 GB at Q4_K_M with an 8K context window. That is the 3.1 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 Holo 3.1 4B on an 8 GB GPU?
Yes, with Q6_K: the 4.0 GB file needs about 5.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Holo 3.1 4B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 1.6 GB, IQ1_M is 1.6 GB, IQ2_XXS is 1.7 GB, IQ2_XS is 1.8 GB, IQ2_S is 1.9 GB and 19 more.
What context length does Holo 3.1 4B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Holo 3.1 4B GGUF?
The files are on Hugging Face in the mradermacher/Holo-3.1-4B-i1-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 4B 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 4B on 8 GB VRAM?
Yes, the Q4_K_M quant uses approximately 4.6 GB of VRAM at 8‑k context, which fits within an 8‑GB budget.
Does this model support vision tasks?
The provided GGUF files do not include vision projection files; vision support is not available in this release.
What license applies to this model?
The model is released under the Apache 2.0 license, allowing free use and modification.