Holo-3.1-9B-GGUF
Holo3.1: Fast & Local Computer Use Agents
Model Description
Holo3.1 is our latest family of Vision-Language Models (VLMs) for computer use agents. Building on Holo3, it expands support beyond browser and desktop automation to mobile environments, introduces native function-calling support for seamless integration with agent frameworks, and enables local deployment through optimized quantized checkpoints.
The Holo3.1 family spans model sizes from 0.8B to 35B-A3B parameters. Across computer use, UI grounding, mobile automation, and business workflows, Holo3.1 delivers strong performance while improving deployment flexibility and cost efficiency.
[!NOTE] For more information, please visit the original model card: https://huggingface.co/Hcompany/Holo-3.1-9B
Model Files
| File Name | Quant Type | File Size | File Link |
|---|---|---|---|
| Holo-3.1-9B.BF16.gguf | BF16 | 17.9 GB | Download |
| Holo-3.1-9B.F16.gguf | F16 | 17.9 GB | Download |
| Holo-3.1-9B.Q2_K.gguf | Q2_K | 3.83 GB | Download |
| Holo-3.1-9B.Q3_K_L.gguf | Q3_K_L | 4.93 GB | Download |
| Holo-3.1-9B.Q3_K_M.gguf | Q3_K_M | 4.62 GB | Download |
| Holo-3.1-9B.Q3_K_S.gguf | Q3_K_S | 4.26 GB | Download |
| Holo-3.1-9B.Q4_0.gguf | Q4_0 | 5.31 GB | Download |
| Holo-3.1-9B.Q4_K_M.gguf | Q4_K_M | 5.63 GB | Download |
| Holo-3.1-9B.Q4_K_S.gguf | Q4_K_S | 5.35 GB | Download |
| Holo-3.1-9B.Q5_0.gguf | Q5_0 | 6.31 GB | Download |
| Holo-3.1-9B.Q5_K_M.gguf | Q5_K_M | 6.47 GB | Download |
| Holo-3.1-9B.Q5_K_S.gguf | Q5_K_S | 6.31 GB | Download |
| Holo-3.1-9B.Q6_K.gguf | Q6_K | 7.36 GB | Download |
| Holo-3.1-9B.Q8_0.gguf | Q8_0 | 9.53 GB | Download |
| Holo-3.1-9B.mmproj-bf16.gguf | mmproj-bf16 | 922 MB | Download |
| Holo-3.1-9B.mmproj-f16.gguf | mmproj-f16 | 922 MB | Download |
| Holo-3.1-9B.mmproj-q8_0.gguf | mmproj-q8_0 | 624 MB | Download |
Quants Usage
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
