# DeskForge-Gemma4-E4B

> DeskForge-Gemma4-E4B is Gemma 4 E4B (instruction-tuned) fine-tuned on 200K grounding examples from DeskForge-1M. Given a desktop screenshot and a natural-language instruction, it answers with the next action as a pyautogui call whose coordinates are fractions of the screen.

- **Organisation:** docling-project
- **Category:** Vision-Language Models
- **Parameters:** 7.9B
- **Context length:** 131,072 tokens
- **Licence:** Apache 2.0 (Commercial use OK)
- **Released:** 2026-10-05
- **Hugging Face:** 449 downloads (30 days), 7 likes

## Estimated memory

| Quant | ≈ GB |
|---|---|
| Q2_K | 3.71 |
| Q3_K_M | 4.95 |
| Q4_K_M | 5.86 |
| Q5_K_M | 6.68 |
| Q6_K | 7.55 |
| Q8_0 | 9.41 |
| F16 | 16.69 |

## Runs with

- [llama.cpp](https://selfhost.directory/project/llamacpp)
- [SGLang](https://selfhost.directory/project/sglang)
- [Transformers](https://github.com/huggingface/transformers)
- [vLLM](https://selfhost.directory/project/vllm)
- [Jan](https://jan.ai) (community)
- [KoboldCpp](https://selfhost.directory/project/koboldcpp) (community)
- [LM Studio](https://lmstudio.ai) (community)
- [LocalAI](https://selfhost.directory/project/localai) (community)
- [Ollama](https://selfhost.directory/project/ollama) (community)

## About

DeskForge-Gemma4-E4B is Gemma 4 E4B (instruction-tuned) fine-tuned on 200K grounding examples from DeskForge-1M. Given a desktop screenshot and a natural-language instruction, it answers with the next action as a pyautogui call whose coordinates are fractions of the screen.

Live demo · Project page · Dataset · Code · Paper · Also available: DeskForge-Qwen3.5-4B

Grounding on DeskForge-1M held-out conditions (accuracy, %). New Scenes are unseen scenes with seen attributes; Theme, App and Resolution hold an appearance preset, three applications and a display resolution out of training entirely.

Grounding on external GUI benchmarks (accuracy, %), none of which is used for training:

Long-horizon task completion (tasks solved). A fixed Qwen3.6-27B planner decides each step and the action model locates its targets, so only the action model differs between the rows:

## Alternatives

- [Qwen/Qwen3.5-9B](https://selfhost.directory/models/qwen/qwen3.5-9b) (9.7B, Apache 2.0, ≈7.22 GB at Q4): Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
- [Qwen/Qwen3-VL-8B-Instruct](https://selfhost.directory/models/qwen/qwen3-vl-8b-instruct) (8.8B, Apache 2.0, ≈6.82 GB at Q4): Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
- [Qwen/Qwen2.5-VL-7B-Instruct](https://selfhost.directory/models/qwen/qwen2.5-vl-7b-instruct) (8.3B, Apache 2.0, ≈5.85 GB at Q4): In the past five months since Qwen2-VL’s release, numerous developers have built new models on the Qwen2-VL vision-language models, providing us with valuable feedback. During this period, we focused on building more useful vision-language models.
- [Zyphra/ZAYA1-VL-8B](https://selfhost.directory/models/zyphra/zaya1-vl-8b) (9.7B, Apache 2.0, ≈6.58 GB at Q4): ZAYA1-VL-8B is a vision-language model (VLM) built upon Zyphra's ZAYA1-8B LLM. It has state-of-the-art performance among VLMs for its size and inference efficiency.
- [Qwen/Qwen3.5-9B-Base](https://selfhost.directory/models/qwen/qwen3.5-9b-base) (9.7B, Apache 2.0, ≈7.22 GB at Q4): Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
- [XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B](https://selfhost.directory/models/xiaomimimo/mimo-v2.6-distill-qwen-9b) (9.4B, MIT, ≈7.08 GB at Q4): MiMo-V2.6-Distill-Qwen-9B is a 9B agentic model developed by Xiaomi MiMo through supervised fine-tuning of Qwen3.5-9B on MiMo-generated data. It covers coding, general-purpose agent tasks, visual coding, and cybersecurity.

More: https://selfhost.directory/models/docling-project/deskforge-gemma4-e4b/alternatives

## Runs well on

- [GeForce RTX 4060](https://selfhost.directory/models/docling-project/deskforge-gemma4-e4b/on/rtx-4060): Q6_K, est. 23 tok/s
- [Apple M4 (16 GB)](https://selfhost.directory/models/docling-project/deskforge-gemma4-e4b/on/apple-m4-16gb): Q8_0, est. 7.8 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/docling-project/deskforge-gemma4-e4b/on/rx-6700-xt): Q8_0, est. 25 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/docling-project/deskforge-gemma4-e4b/on/rtx-3060): Q8_0, est. 23 tok/s
- [Arc B580](https://selfhost.directory/models/docling-project/deskforge-gemma4-e4b/on/arc-b580): Q8_0, est. 30 tok/s
- [Tesla T4](https://selfhost.directory/models/docling-project/deskforge-gemma4-e4b/on/tesla-t4): Q8_0, est. 21 tok/s

## Similar size

- [Qwen/Qwen3.5-9B](https://selfhost.directory/models/qwen/qwen3.5-9b) (9.7B)
- [Qwen/Qwen3-VL-8B-Instruct](https://selfhost.directory/models/qwen/qwen3-vl-8b-instruct) (8.8B)
- [Qwen/Qwen2.5-VL-7B-Instruct](https://selfhost.directory/models/qwen/qwen2.5-vl-7b-instruct) (8.3B)
- [XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B](https://selfhost.directory/models/xiaomimimo/mimo-v2.6-distill-qwen-9b) (9.4B)
- [openbmb/MiniCPM-V-4_5](https://selfhost.directory/models/openbmb/minicpm-v-4_5) (8.7B)
- [Cloudflare/clef-flash](https://selfhost.directory/models/cloudflare/clef-flash) (9.4B)

## FAQ

**How much VRAM does DeskForge-Gemma4-E4B need?**
About 5.9 GB at Q4_K_M with an 8K context. Q8_0 needs about 9.4 GB and full precision about 17 GB. Longer contexts need more memory for the KV cache.

**Can DeskForge-Gemma4-E4B run on the RTX 4060?**
Yes. It fits at Q6_K (about 7.2 GB), at an estimated 23 tokens/s. It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.

**Can I use DeskForge-Gemma4-E4B commercially?**
Yes. It is released under Apache 2.0. Permissive: use, modify and sell freely; keep the notice and licence text.

**What is the context length of DeskForge-Gemma4-E4B?**
131,072 tokens (128K). The full window needs far more memory than an 8K context.

**How do I run DeskForge-Gemma4-E4B with Ollama or llama.cpp?**
With Ollama: ollama run hf.co/mradermacher/DeskForge-Gemma4-E4B-GGUF:Q4_K_M. With llama.cpp: llama-server -hf mradermacher/DeskForge-Gemma4-E4B-GGUF:Q4_K_M, which starts an OpenAI-compatible server.

## Links

- huggingface: https://huggingface.co/docling-project/DeskForge-Gemma4-E4B
- homepage: https://saidgurbuz.github.io/deskforge/
- github: https://github.com/Saidgurbuz/deskforge
- paper: https://arxiv.org/abs/2610.02320
- demo: https://huggingface.co/spaces/docling-project/DeskForge

---
Source: https://selfhost.directory/models/docling-project/deskforge-gemma4-e4b