Holo 3.1 0.8B needs about 1.6 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 0.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
Holo 3.1 0.8B – Vision‑Language model for local computer use agents
Holo 3.1 0.8B is a 1.01‑billion‑parameter vision‑language model built on Qwen 3.5. It supports reasoning and tool use, and is optimized for local inference with a 262144‑token context window. The model is released under Apache 2.0.
Good at
- reasoning
- tools
- local inference
Limits
- trained context 262144 tokens
- requires 1.3‑1.7 GB VRAM at 8k context
- no external vision files in GGUF
Best for
- desktop automation
- mobile UI grounding
- enterprise workflow scripts
Who it’s for. Developed by H Company, this model is aimed at developers building local agents that need reasoning and tool‑calling capabilities. It is suitable for applications that run entirely on a single machine.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.9 GB | Fits | Get file → | |
| IQ1_S | 0.4 GB | 1.3 GB | Fits | Get file → | |
| IQ1_M | 0.4 GB | 1.3 GB | Fits | Get file → | |
| IQ2_XXS | 0.4 GB | 1.3 GB | Fits | Get file → | |
| IQ2_XS | 0.4 GB | 1.3 GB | Fits | Get file → | |
| IQ2_S | 0.5 GB | 1.4 GB | Fits | Get file → | |
| IQ2_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q2_K_S | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q2_K | 0.5 GB | 1.4 GB | Fits | Get file → | |
| IQ3_XXS | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_S | 0.5 GB | 1.4 GB | Fits | Get file → | |
| IQ3_XS | 0.6 GB | 1.5 GB | Fits | Get file → | |
| IQ3_S | 0.6 GB | 1.5 GB | Fits | Get file → | |
| IQ3_M | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_M | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_L | 0.6 GB | 1.5 GB | Fits | Get file → | |
| IQ4_XS | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q4_0 | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q4_K_S | 0.6 GB | 1.6 GB | Fits | Get file → | |
| IQ4_NL | 0.7 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 0.7 GB | 1.6 GB | Fits | Get file → | |
| Q4_1 | 0.7 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_S | 0.7 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_M | 0.8 GB | 1.7 GB | Fits | Get file → | |
| Q6_K | 0.8 GB | 1.7 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.67 GB file, 1.6 GB memory). For 4 GB VRAM, IQ1_S or IQ1_M (0.41–0.42 GB file, 1.3 GB memory) are appropriate. For 2 GB VRAM, IQ1_S or IQ1_M remain the best options.
What GPU do you need for Holo 3.1 0.8B?
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 Q6_K (0.8 GB file, about 1.7 GB in use).
Which Holo 3.1 0.8B quant should you choose?
Q4_K_M is the usual starting point for Holo 3.1 0.8B: it balances file size and quality well. Here it is a 0.7 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 0.8B
How much VRAM does Holo 3.1 0.8B need?
About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.7 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 0.8B on an 8 GB GPU?
Yes, with Q6_K: the 0.8 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Holo 3.1 0.8B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 0.4 GB, IQ1_M is 0.4 GB, IQ2_XXS is 0.4 GB, IQ2_XS is 0.4 GB, IQ2_S is 0.5 GB and 19 more.
What context length does Holo 3.1 0.8B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download Holo 3.1 0.8B GGUF?
The files are on Hugging Face in the mradermacher/Holo-3.1-0.8B-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 0.8B 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 0.8B on 4 GB VRAM?
Yes, using IQ1_S or IQ1_M quantizations which require about 1.3 GB VRAM at 8k context.
Does the model support vision tasks?
The GGUF files are vision‑model compatible, but mmproj files are provided separately in the static repository.
What license does it use?
The model is released under the Apache 2.0 License.