Instructions to use aifeifei799/OmniCoder-VL-9B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aifeifei799/OmniCoder-VL-9B-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("aifeifei799/OmniCoder-VL-9B-GGUF", dtype="auto")

llama-cpp-python

How to use aifeifei799/OmniCoder-VL-9B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="aifeifei799/OmniCoder-VL-9B-GGUF",
	filename="OmniCoder-VL-9B-q8_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use aifeifei799/OmniCoder-VL-9B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf aifeifei799/OmniCoder-VL-9B-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf aifeifei799/OmniCoder-VL-9B-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf aifeifei799/OmniCoder-VL-9B-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf aifeifei799/OmniCoder-VL-9B-GGUF:Q8_0

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 aifeifei799/OmniCoder-VL-9B-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf aifeifei799/OmniCoder-VL-9B-GGUF:Q8_0

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 aifeifei799/OmniCoder-VL-9B-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf aifeifei799/OmniCoder-VL-9B-GGUF:Q8_0

Use Docker

docker model run hf.co/aifeifei799/OmniCoder-VL-9B-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use aifeifei799/OmniCoder-VL-9B-GGUF with Ollama:
```
ollama run hf.co/aifeifei799/OmniCoder-VL-9B-GGUF:Q8_0
```

Unsloth Studio new

How to use aifeifei799/OmniCoder-VL-9B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for aifeifei799/OmniCoder-VL-9B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for aifeifei799/OmniCoder-VL-9B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for aifeifei799/OmniCoder-VL-9B-GGUF to start chatting

Pi new

How to use aifeifei799/OmniCoder-VL-9B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf aifeifei799/OmniCoder-VL-9B-GGUF:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "aifeifei799/OmniCoder-VL-9B-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use aifeifei799/OmniCoder-VL-9B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf aifeifei799/OmniCoder-VL-9B-GGUF:Q8_0

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 aifeifei799/OmniCoder-VL-9B-GGUF:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use aifeifei799/OmniCoder-VL-9B-GGUF with Docker Model Runner:
```
docker model run hf.co/aifeifei799/OmniCoder-VL-9B-GGUF:Q8_0
```

Lemonade

How to use aifeifei799/OmniCoder-VL-9B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull aifeifei799/OmniCoder-VL-9B-GGUF:Q8_0

Run and chat with the model

lemonade run user.OmniCoder-VL-9B-GGUF-Q8_0

List all available models

lemonade list

OmniCoder-9B

Running on Cyber-Crawfish Ultra, the local beast.

A 9B coding agent fine-tuned on 425K agentic trajectories.

!! 3/12/26 Update -> Install For Your Coding Agents

Get Started | Benchmarks | GGUF Downloads

Overview

OmniCoder-9B is a 9-billion parameter coding agent model built by Tesslate, fine-tuned on top of Qwen3.5-9B's hybrid architecture (Gated Delta Networks interleaved with standard attention). It was trained on 425,000+ curated agentic coding trajectories spanning real-world software engineering tasks, tool use, terminal operations, and multi-step reasoning.

The training data was specifically built from Claude Opus 4.6 agentic and coding reasoning traces, targeting scaffolding patterns from Claude Code, OpenCode, Codex, and Droid. The dataset includes successful trajectories from models like Claude Opus 4.6, GPT-5.4, GPT-5.3-Codex, and Gemini 3.1 Pro.

The model shows strong agentic behavior: it recovers from errors (read-before-write), responds to LSP diagnostics, and uses proper edit diffs instead of full rewrites. These patterns were learned directly from the real-world agent trajectories it was trained on.

Key Features

Trained on Frontier Agent Traces : Built from Claude Opus 4.6, GPT-5.3-Codex, GPT-5.4, and Gemini 3.1 Pro agentic coding trajectories across Claude Code, OpenCode, Codex, and Droid scaffolding
Hybrid Architecture : Inherits Qwen3.5's Gated Delta Networks interleaved with standard attention for efficient long-context processing
262K Native Context : Full 262,144 token context window, extensible to 1M+
Error Recovery : Learns read-before-write patterns, responds to LSP diagnostics, and applies minimal edit diffs instead of full rewrites
Thinking Mode : Supports <think>...</think> reasoning chains for complex problem decomposition
Apache 2.0 : Fully open weights, no restrictions

Benchmarks

Benchmark	OmniCoder-9B	Qwen3.5-9B	Qwen3-Next-80B	GPT-OSS-120B	GPT-OSS-20B	GLM-4.7-Flash	GLM 4.7	Claude Haiku 4.5
AIME 2025 (pass@5)	90				91.7	91.6
GPQA Diamond (pass@1)	83.8	81.7	77.2	80.1	71.5			73
GPQA Diamond (pass@3)	86.4
Terminal-Bench 2.0	23.6	14.6					33.4	27

GPQA Diamond pass@1: 83.8% (166/198). +2.1 points over the Qwen3.5-9B base model (81.7). At pass@3: 86.4 (171/198).
AIME 2025 pass@5: 90% (27/30).
Terminal-Bench 2.0: 23.6% (21/89). +8.99 points (+61% improvement) over the Qwen3.5-9B base model (14.6%, 13/89).

Quickstart

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Tesslate/OmniCoder-9B"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")

messages = [
    {"role": "system", "content": "You are a helpful coding assistant."},
    {"role": "user", "content": "Write a Python function to find the longest common subsequence of two strings."},
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer([text], return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=2048, temperature=0.6, top_p=0.95, top_k=20)
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True))

vLLM

vllm serve Tesslate/OmniCoder-9B --tensor-parallel-size 1 --max-model-len 65536

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="token")
response = client.chat.completions.create(
    model="Tesslate/OmniCoder-9B",
    messages=[{"role": "user", "content": "Explain the difference between a mutex and a semaphore."}],
    temperature=0.6,
)
print(response.choices[0].message.content)

llama.cpp (GGUF)

llama-cli --hf-repo Tesslate/OmniCoder-9B-GGUF --hf-file omnicoder-9b-q4_k_m.gguf -p "Your prompt" -c 8192

All quantizations: aifeifei799/OmniCoder-VL-9B-GGUF

Training Details


Base Model	Qwen3.5-9B
Method	LoRA SFT (r=64, alpha=32)
Dataset	425K agentic trajectories from 5 sources
Packing	Sample packing with 99.35% efficiency
Hardware	4x NVIDIA H200 (DDP)
Framework	Axolotl
Precision	bf16
Optimizer	AdamW (lr=2e-4, cosine schedule)

Architecture

OmniCoder inherits Qwen3.5-9B's hybrid architecture:

Gated Delta Networks : Linear attention layers interleaved with standard attention for efficient long-range dependencies
VLM Backbone : Built on Qwen3_5ForConditionalGeneration

Recommended Sampling Parameters

Parameter	Value
Temperature	0.6
Top-P	0.95
Top-K	20
Presence Penalty	0.0

For agentic / tool-calling tasks, consider lower temperature (0.2-0.4) for more deterministic behavior.

Limitations

Performance on non-English tasks has not been extensively evaluated
Tool-calling format is flexible but works best with the scaffolding patterns seen in training

Acknowledgments

Special thanks to the Axolotl team and the discussion in axolotl#3453 for helping get Qwen3.5 packing support working.

Citation

@misc{omnicoder2025,
  title={OmniCoder-9B: A Frontier Open Coding Agent},
  author={Tesslate},
  year={2025},
  url={https://huggingface.co/Tesslate/OmniCoder-9B}
}

Built by Tesslate

Downloads last month: 36

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

8-bit

Inference Providers NEW

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

Model tree for aifeifei799/OmniCoder-VL-9B-GGUF

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

Tesslate/OmniCoder-9B

Quantized

(19)

this model