Instructions to use CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-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 CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-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 CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-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 CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-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 CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-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 CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF with Ollama:
```
ollama run hf.co/CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-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": "CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF with Docker Model Runner:
```
docker model run hf.co/CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF:Q4_K_M
```

Lemonade

How to use CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-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 CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-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 CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-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 "CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-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"

PREVIEW 1.5 — GGUF quants for testing. Final release will follow after think-SFT, native MTP and updated quants.

CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF

GGUF quantizations of CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B — MoE decoder (~33B total / ~13B active per token), DPO-aligned + SFT-reinforced for code and cybersecurity (PT/EN).

Quants

File	Size	VRAM/RAM needed (approx.)
`CobrIX-1.5-preview-Coder-Flash-33B-A13B-Q5_K_M.gguf`	22,0 GB	~24 GB
`CobrIX-1.5-preview-Coder-Flash-33B-A13B-Q4_K_M.gguf`	18,9 GB	~20 GB

Usage (Ollama)

FROM ./CobrIX-1.5-preview-Coder-Flash-33B-A13B-Q5_K_M.gguf

TEMPLATE """{{- if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
"""

PARAMETER stop "<|im_end|>"
PARAMETER num_ctx 8192

ollama create cobrix15-flash-q5 -f Modelfile
ollama run cobrix15-flash-q5 "Explique SQL injection e como mitigar."

Usage (llama.cpp)

llama-cli -m CobrIX-1.5-preview-Coder-Flash-33B-A13B-Q5_K_M.gguf \
  --jinja -p "<|im_start|>user\nExplique SQL injection<|im_end|>\n<|im_start|>assistant\n" -n 300

🌐 CobrIX Coder and CobrIX Code Models — Early Access

CobrIX Coder is the AI ecosystem that runs and gives you instant access to our models — including CobrIX-1.0-Coder-Flash-MoE, CobrIX-1.0-Coder-Full-MoE, and the brand-new 1.5 preview family.

✨ Try CobrIX Coder Live Now

https://cobrix.vercel.app/coder

Explore the platform, test the models in real time, and follow the evolution of CobrIX Code as it happens.

⚡ Flash First — Priority Access Coming Soon!

We're gearing up for the big public launch! As soon as our waitlist hits a strong number, we'll unlock the Flash heroes first — CobrIX-1.0-Coder-Flash and CobrIX-1.5-Coder-Flash — as soon as everything is polished and ready.

Early sign-ups get priority access. Secure your spot today and be among the very first to experience the next generation! 🌟

📋 Interest List — Join the Waitlist

Want to be the first to know when the CobrIX AI ecosystem and CobrIX Code go fully public?

👉 Visit: https://cobrix.vercel.app/coder

Registered users will receive an email the moment CobrIX Code becomes available.

We currently have the funds to host CobrIX-1.0-Coder-Flash-33B-A13B on an RTX 6000 Ada Generation (48GB VRAM), supporting 50–100 concurrent users.

🚀 Join the waitlist now and be first in line when CobrIX Code launches!

Feedback — help make it better

Found a flaw or have an idea? 📧 suporte.cobrix@gmail.com — send the prompt, the output, what you expected, and how to improve it.

Donations for Infrastructure

Support open-source CobrIX development:

Bitcoin (BTC)

bc1q8mu8fjak4y84qj4dlk8pu4d3zhknm92zra4r4m

Ethereum (ETH / ERC-20)

0x8D9187dEa0a77390ef668361cd5b236DE54af2BB

Solana (SOL)

GQR2jZnWuWP1c3dbuz4mC7ZnyveacBKy63q8qf9nj8bp

CobrIX — Open AI infrastructure and custom model research.

Downloads last month: 145

GGUF

Model size

33B params

Architecture

qwen35moe

Hardware compatibility

4-bit

5-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

empero-ai/Qwythos-9B-Claude-Mythos-5-1M

Finetuned

empero-ai/Qwythos-9B-v2

Finetuned

CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B

Quantized

(1)

this model

Collection including CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF

CobrIX-1.5-Preview-Coder

Collection

4 items • Updated 3 days ago