Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
DeskForge-Gemma4-E4B
docling-project·Instruct·released 5 Oct 2026
ollama run hf.co/mradermacher/DeskForge-Gemma4-E4B-GGUF:Q4_K_MDeskForge-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.
How much VRAM does DeskForge-Gemma4-E4B need?
At Q4_K_M DeskForge-Gemma4-E4B needs about 5.9 GB with an 8K context (5.9 GB at Q4, 17 GB at full precision). Pick your GPU to see what fits and how fast it runs.
Needs: ≈6.3 GB · Q4_K_M · 8K context — Pick a GPU to check the fit.
Advanced: context 8K · KV cache 16-bit
Smallest GPU for each quant and context (KV cache 16-bit)
| Quantisation | 4K | 8K | 16K | 32K | 64K | 128K |
|---|---|---|---|---|---|---|
| Q3_K_M | ||||||
| Q4_K_M | ||||||
| Q5_K_M | ||||||
| Q6_K | ||||||
| Q8_0 | ||||||
| FP16 |
≤16 GB card24–32 GB48–96 GBmore
| Quantisation | Total |
|---|---|
| Q2_KHeavy lossSmallest, noticeably worse quality | ≈5.4 GB |
| Q3_K_MNoticeable lossSmall, some quality loss | ≈5.9 GB |
| Q4_K_MrecommendedSmall lossRecommended default for local use | ≈6.3 GB |
| Q5_K_MNear-losslessNear-lossless for most tasks | ≈6.8 GB |
| Q6_KNear-losslessPractically lossless | ≈7.2 GB |
| Q8_0LosslessLossless in practice, twice the size of Q4 | ≈9.0 GB |
| FP16 / BF16LosslessFull precision, as released | ≈16 GB |
Estimates for 8K tokens of context: weights + KV cache + runtime overhead. Speed assumes memory-bound decoding at your GPU’s bandwidth. Pick a GPU above and the fit column checks every row against it. Weights marked “file” use the real GGUF download size; “est.” rows are computed from the parameter count.
How to pick a quant
Take the biggest quant that fits with room left for context. Q4_K_M is the usual sweet spot. Below Q4 quality drops fast, above Q6 you mostly pay memory for nothing. Big models (70B+, large MoE) tolerate low quants better than small ones.
- LosslessF16, Q8_0
- Near-losslessQ6_K, Q5_K_M
- Small lossQ5_K_S, Q4_K_M, IQ4_NL, IQ4_XS, Q4_K_S
- Noticeable lossQ4_0, Q3_K_L, Q3_K_M, IQ3_M
- Heavy lossIQ3_XXS, Q3_K_S, IQ2_M, Q2_K
Typical quality loss, not measured per model. Tiers come from KL divergence against FP16 on Llama 3 8B: llama.cpp perplexity README: LLaMA 3 8B scoreboard (KLD and ΔPPL vs FP16, Wikitext-2); llama.cpp quantize tool: ΔPPL per quant type @ Llama-3-8B
How much context fits?
At 8K context, Q4_K_M needs ≈6.3 GB(4.9 GB weights + 0.7 GB KV cache + 0.8 GB overhead). Pick a GPU above to see how much context fits.
Weights + overheadKV cache
Can the RTX 4060 run DeskForge-Gemma4-E4B? →
Speed vs quality per quant
Smaller quants run faster and fit in less memory, but lose quality.
Fits in VRAMTight fitCPU offload✕ won't runQuality is typical KL divergence vs FP16, not measured for this model.
Real-world speed of DeskForge-Gemma4-E4B
Tokens per second measured by people running it at home. A GPU shows a median once 3 reports agree on the same setup. Reports far from our estimate wait for a review. Measure yours with llama-bench →
No medians yet. Be one of the first 3 to report a setup.
All reports
Run DeskForge-Gemma4-E4B locally
--quantQ4_K_Mdefault; pick your GPU to tailor itmradermacher/DeskForge-Gemma4-E4B-GGUF
ollama run hf.co/mradermacher/DeskForge-Gemma4-E4B-GGUF:Q4_K_M llama-server -hf mradermacher/DeskForge-Gemma4-E4B-GGUF:Q4_K_MDownloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
lms get mradermacher/DeskForge-Gemma4-E4B-GGUF@Q4_K_MThen load it from the LM Studio app or with `lms load`.
vllm serve docling-project/DeskForge-Gemma4-E4Bservices:
vllm:
image: vllm/vllm-openai:latest
command: docling-project/DeskForge-Gemma4-E4B
ports:
- "8000:8000"
ipc: host
volumes:
- ~/.cache/huggingface:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]API on port 8000.
sglang serve docling-project/DeskForge-Gemma4-E4B --host 0.0.0.0 --port 30000services:
sglang:
image: lmsysorg/sglang:latest
command: sglang serve docling-project/DeskForge-Gemma4-E4B --host 0.0.0.0 --port 30000
ports:
- "30000:30000"
ipc: host
volumes:
- ~/.cache/huggingface:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]API on port 30000.
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="docling-project/DeskForge-Gemma4-E4B", dtype="auto", device_map="auto")
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
{"type": "text", "text": "Describe this image."},
],
}
]
out = pipe(text=messages, max_new_tokens=256)
print(out[0]["generated_text"][-1]["content"])Quantised versions and downloads
| Repository | Format | Quant | Size |
|---|---|---|---|
| mradermacher/DeskForge-Gemma4-E4B-GGUF | GGUF | Q2_K | 4.4 GB |
| mradermacher/DeskForge-Gemma4-E4B-GGUF | GGUF | Q3_K_S | 4.6 GB |
| mradermacher/DeskForge-Gemma4-E4B-GGUF | GGUF | Q3_K_M | 4.8 GB |
| mradermacher/DeskForge-Gemma4-E4B-GGUF | GGUF | Q3_K_L | 5.0 GB |
| mradermacher/DeskForge-Gemma4-E4B-GGUF | GGUF | IQ4_XS | 5.1 GB |
| mradermacher/DeskForge-Gemma4-E4B-GGUF | GGUF | Q4_K_S | 5.2 GB |
| mradermacher/DeskForge-Gemma4-E4B-GGUF | GGUF | Q4_K_M | 5.3 GB |
| mradermacher/DeskForge-Gemma4-E4B-GGUF | GGUF | Q5_K_S | 5.6 GB |
| mradermacher/DeskForge-Gemma4-E4B-GGUF | GGUF | Q5_K_M | 5.7 GB |
| mradermacher/DeskForge-Gemma4-E4B-GGUF | GGUF | Q6_K | 6.2 GB |
About 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. 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:
Full model card on Hugging Face →Alternatives to DeskForge-Gemma4-E4B
All alternatives →Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
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.
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.
FLUX 3 Image Klein Prompt Upsampler is a 9B vision-language model that expands a short image request into the detailed prompt FLUX 3 Image Klein works best with. It takes the request, up to 10 reference images and an optional list of bounding boxes, and returns one prompt.
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
DeskForge-Gemma4-E4B 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.
Rate this model
Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.
0 comments