Instructions to use Atlas3D/JEV-27B-VL-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Atlas3D/JEV-27B-VL-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Atlas3D/JEV-27B-VL-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Atlas3D/JEV-27B-VL-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Atlas3D/JEV-27B-VL-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Atlas3D/JEV-27B-VL-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Atlas3D/JEV-27B-VL-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Atlas3D/JEV-27B-VL-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Atlas3D/JEV-27B-VL-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Atlas3D/JEV-27B-VL-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Atlas3D/JEV-27B-VL-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Atlas3D/JEV-27B-VL-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Atlas3D/JEV-27B-VL-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Atlas3D/JEV-27B-VL-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Atlas3D/JEV-27B-VL-GGUF:Q4_K_M

Ollama
How to use Atlas3D/JEV-27B-VL-GGUF with Ollama:
```
ollama run hf.co/Atlas3D/JEV-27B-VL-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Atlas3D/JEV-27B-VL-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Atlas3D/JEV-27B-VL-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Atlas3D/JEV-27B-VL-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Atlas3D/JEV-27B-VL-GGUF with Docker Model Runner:
```
docker model run hf.co/Atlas3D/JEV-27B-VL-GGUF:Q4_K_M
```

Lemonade

How to use Atlas3D/JEV-27B-VL-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Atlas3D/JEV-27B-VL-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.JEV-27B-VL-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Atlas3D/JEV-27B-VL-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Atlas3D/JEV-27B-VL-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Atlas3D/JEV-27B-VL-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Atlas3D/JEV-27B-VL-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Atlas3D/JEV-27B-VL-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Atlas3D/JEV-27B-VL-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Atlas3D/JEV-27B-VL-GGUF

GGUF builds of autotrust/JEV-27B-VL for llama.cpp's native decision endpoint /v1/systemone, with JEV's own readout: false/true for yes/no, the digits 0–5 for scores, and letters for choices, plus its decision-head bias and calibrated temperatures. These are also the builds for older GPUs such as V100s, which cannot run FP8/FP4 checkpoints.

Requires a patched llama.cpp (for now). The jev decision type is not in upstream llama.cpp yet. Apply llama.cpp-jev.patch (made against upstream bed0a85) and build. It adds the converter class, the GGUF metadata keys and the server readout.

file	size	top choice agrees with bf16 (309 decisions)	largest prob. change
`JEV-27B-VL-BF16.gguf`	54 GB	99.4% (307/309): llama.cpp vs vLLM at full precision	0.017
`JEV-27B-VL-Q8_0.gguf`	29 GB	99.0% (306/309), recommended	0.023
`JEV-27B-VL-Q4_K_M.gguf` ⚠️	17 GB	92.9% (287/309): less accurate, see below	0.102
`mmproj-BF16.gguf`, `mmproj-Q8_0.gguf`	0.9 / 0.6 GB	vision projector

⚠️ Q4_K_M is less accurate. About 1 decision in 14 differs from full precision. Prefer Q8_0 when it fits. Q4_K_M is for 24 GB-class cards.

The reference is autotrust's own vLLM server (serve_decide.py) at bf16, on the same recorded requests. Measured on an RTX PRO 6000 Blackwell: about 80 ms per decision for Q8_0, sequential, with prompt caching off. VRAM in use: BF16 56.6 GB, Q8_0 33.6 GB, Q4_K_M 22.7 GB (4k context). V100 (sm_70) builds compile with CUDA 12.x (CUDA 13 dropped sm_70). Results on real V100 hardware have not been measured yet. This is a narrow test of the decision head. Free-text generation was not separately benchmarked.

Serve

llama-server --model JEV-27B-VL-Q8_0.gguf --mmproj mmproj-BF16.gguf --n-gpu-layers 999 \
  --ctx-size 4096 --flash-attn on --jinja --host 127.0.0.1 --port 8080
curl -s localhost:8080/v1/systemone -H 'Content-Type: application/json' -d '{"state": "...",
  "questions": {"q": {"type": "choice", "instructions": "...", "criteria": {"a": null, "b": null}}}}'

License

Apache-2.0, as with the original. This is a modified (converted and quantized) version of autotrust/JEV-27B-VL, which is itself based on Qwen/Qwen3.8-27B. LICENSE is included unchanged. The patch modifies llama.cpp (MIT).

Downloads last month: 7,447

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

8-bit

16-bit

Model tree for Atlas3D/JEV-27B-VL-GGUF

Base model

Qwen/Qwen3.8-27B

Adapter

autotrust/JEV-27B-VL

Quantized

(10)

this model

Atlas3D
/

JEV-27B-VL-GGUF

Atlas3D/JEV-27B-VL-GGUF

Serve

License

Model tree for Atlas3D/JEV-27B-VL-GGUF

Space using Atlas3D/JEV-27B-VL-GGUF 1