Instructions to use prithivMLmods/OpenJev-Flash-9B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/OpenJev-Flash-9B-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("zero-shot-classification", model="prithivMLmods/OpenJev-Flash-9B-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/OpenJev-Flash-9B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/OpenJev-Flash-9B-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 prithivMLmods/OpenJev-Flash-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/OpenJev-Flash-9B-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 prithivMLmods/OpenJev-Flash-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/OpenJev-Flash-9B-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 prithivMLmods/OpenJev-Flash-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/OpenJev-Flash-9B-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 prithivMLmods/OpenJev-Flash-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/OpenJev-Flash-9B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/OpenJev-Flash-9B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use prithivMLmods/OpenJev-Flash-9B-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/OpenJev-Flash-9B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use prithivMLmods/OpenJev-Flash-9B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/OpenJev-Flash-9B-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": "prithivMLmods/OpenJev-Flash-9B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use prithivMLmods/OpenJev-Flash-9B-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/OpenJev-Flash-9B-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/OpenJev-Flash-9B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/OpenJev-Flash-9B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.OpenJev-Flash-9B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use prithivMLmods/OpenJev-Flash-9B-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 prithivMLmods/OpenJev-Flash-9B-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 prithivMLmods/OpenJev-Flash-9B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use prithivMLmods/OpenJev-Flash-9B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/OpenJev-Flash-9B-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 "prithivMLmods/OpenJev-Flash-9B-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"

OpenJev-Flash-9B-GGUF

OpenJev Flash 9B is the small, fast member of the OpenJev family: an open-weights decision model built on Qwen3.5-9B and fine-tuned with supervised and teacher-guided fine-tuning, though the training recipe and data are not released. It answers typed questions about text (choice with up to 52 options per pass, yes/no noul, or ordered score) with a calibrated probability for every option. The labels are written in the request, so a new task or domain needs a JSON change, not retraining. It reads the scores of the option letters at the first output position, so there is no free-form text to parse. Each decision takes about 40 ms on one H100 (FP8), 1.6x faster than OpenJev 27B, at roughly 4.6 US cents per 1,000 decisions. On JevBench's 231 public items it gets 188 correct (81.4%), on par with Cloudflare's Clef-Flash (82.3%) and ahead of Kev-9B and Nimble 9B (both 79.2%), and it does best on ambiguous cases and on judging responses. No JevBench item was used in training or tuning. On the card's own 10,000-question mix from 34 public sources it scores 79.4%, behind OpenJev 27B (84.1%) and the hosted Jev API (85.4%). It is served with vLLM plus a small /v1/systemone helper shim that mirrors the hosted Jev API and the 27B's interface, with FP8, MLX 4-bit and 8-bit, and GGUF builds available. The weights are CC BY-NC 4.0, so non-commercial use only unless you license it commercially, and the helper and serve files are Apache 2.0. The project is independent of TypeSafe. openjev/OpenJev-Flash-9B on Hugging Face — OpenJev-Flash-9B.

Model Files

File Name	Quant Type	File Size	File Link	Description
OpenJev-Flash-9B.BF16.gguf	BF16	17.9 GB	Link	Full BF16 weights. Highest quality, largest file size.
OpenJev-Flash-9B.Q3_K_L.gguf	Q3_K_L	4.93 GB	Link	Lower quality but usable, good for low RAM availability.
OpenJev-Flash-9B.Q3_K_M.gguf	Q3_K_M	4.62 GB	Link	Low quality.
OpenJev-Flash-9B.Q4_K_M.gguf	Q4_K_M	5.63 GB	Link	Good quality, default size for most use cases, recommended.
OpenJev-Flash-9B.Q4_K_S.gguf	Q4_K_S	5.35 GB	Link	Slightly lower quality with more space savings, recommended.
OpenJev-Flash-9B.Q5_K_M.gguf	Q5_K_M	6.47 GB	Link	High quality, recommended.
OpenJev-Flash-9B.Q5_K_S.gguf	Q5_K_S	6.31 GB	Link	High quality, recommended.
OpenJev-Flash-9B.Q6_K.gguf	Q6_K	7.36 GB	Link	Very high quality, near perfect, recommended.
OpenJev-Flash-9B.mmproj-bf16.gguf	mmproj-bf16	922 MB	Link	Multimodal projection file in BF16 format. Used for vision/language models.