Instructions to use DarkKnighToS223/FLv1.1-9B-low-level with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DarkKnighToS223/FLv1.1-9B-low-level with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="DarkKnighToS223/FLv1.1-9B-low-level",
	filename="FLv1.1-9B-low-level.Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use DarkKnighToS223/FLv1.1-9B-low-level 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 DarkKnighToS223/FLv1.1-9B-low-level:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf DarkKnighToS223/FLv1.1-9B-low-level:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf DarkKnighToS223/FLv1.1-9B-low-level:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf DarkKnighToS223/FLv1.1-9B-low-level: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 DarkKnighToS223/FLv1.1-9B-low-level:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf DarkKnighToS223/FLv1.1-9B-low-level: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 DarkKnighToS223/FLv1.1-9B-low-level:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DarkKnighToS223/FLv1.1-9B-low-level:Q4_K_M

Use Docker

docker model run hf.co/DarkKnighToS223/FLv1.1-9B-low-level:Q4_K_M

LM Studio
Jan
Ollama
How to use DarkKnighToS223/FLv1.1-9B-low-level with Ollama:
```
ollama run hf.co/DarkKnighToS223/FLv1.1-9B-low-level:Q4_K_M
```

Unsloth Studio

How to use DarkKnighToS223/FLv1.1-9B-low-level 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 DarkKnighToS223/FLv1.1-9B-low-level 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 DarkKnighToS223/FLv1.1-9B-low-level to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DarkKnighToS223/FLv1.1-9B-low-level to start chatting

How to use DarkKnighToS223/FLv1.1-9B-low-level with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DarkKnighToS223/FLv1.1-9B-low-level:Q4_K_M

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": "DarkKnighToS223/FLv1.1-9B-low-level:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use DarkKnighToS223/FLv1.1-9B-low-level with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DarkKnighToS223/FLv1.1-9B-low-level: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 DarkKnighToS223/FLv1.1-9B-low-level:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use DarkKnighToS223/FLv1.1-9B-low-level with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DarkKnighToS223/FLv1.1-9B-low-level: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 "DarkKnighToS223/FLv1.1-9B-low-level: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"

Docker Model Runner
How to use DarkKnighToS223/FLv1.1-9B-low-level with Docker Model Runner:
```
docker model run hf.co/DarkKnighToS223/FLv1.1-9B-low-level:Q4_K_M
```

Lemonade

How to use DarkKnighToS223/FLv1.1-9B-low-level with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DarkKnighToS223/FLv1.1-9B-low-level:Q4_K_M

Run and chat with the model

lemonade run user.FLv1.1-9B-low-level-Q4_K_M

List all available models

lemonade list

Flare-9B v1.1 — Low-Level & Legacy Code

A 9B coding model that speaks the languages most models forgot.

Modern code models are great at Python, JavaScript and the usual suspects — and useless the moment you hand them a COBOL payroll routine or a hand-written x86 assembly stub. Flare-9B v1.1 is built for exactly that gap: COBOL, assembly and C, the languages that still run banks, mainframes and firmware, with almost no model support behind them.

It's a continued-pretraining pass over Tesslate/OmniCoder-9B on a curated corpus of real low-level and legacy code — tuned to add legacy fluency without throwing away the strong general coding ability of the base.

Why it exists

Ask a top open coding model to write COBOL and you usually get confident nonsense — missing DATA DIVISION, undeclared variables, code that doesn't compile. That's not a knock on those models; there's simply very little clean COBOL in their training data.

Flare-9B v1.1 was trained on a cleaned, code-only legacy corpus (no scraped prose, no chat transcripts — just real programs), so it produces COBOL that actually compiles and runs.

Benchmarks

All numbers are pass@1, executed — every sample is compiled (gcc / g++ / GnuCOBOL / mono) and run against test cases. No self-reported or LLM-judged scores.

Language	Base (OmniCoder-9B)	Flare-9B v1.1
COBOL	0%	50%
C	87%	81%
C++	87%	81%
C#	75%	69%
Assembly x86-64	4%	10%

The headline: COBOL goes from completely unusable to genuinely useful — the base model scores a flat zero, Flare v1.1 solves half of a 40-task executable COBOL suite. General C-family ability stays strong (~80%+), so you get legacy fluency as an addition, not a trade-down. Raw hand-written assembly remains hard for any 9B model, but the simple cases land cleanly.

Best use

This model is completion-oriented — it shines when you give it code context (a function signature, a program skeleton, a divisions header) rather than long chat instructions.

from transformers import AutoModelForImageTextToText, AutoTokenizer

tok = AutoTokenizer.from_pretrained("DarkKnighToS223/Flare-9B-low-level-programming")
model = AutoModelForImageTextToText.from_pretrained(
    "DarkKnighToS223/Flare-9B-low-level-programming",
    device_map="auto", trust_remote_code=True)

prompt = """*> GnuCOBOL: compute 15 + 27 and DISPLAY the result.
       IDENTIFICATION DIVISION.
       PROGRAM-ID. MAIN.
"""
inputs = tok(prompt, return_tensors="pt").to(model.device)
print(tok.decode(model.generate(**inputs, max_new_tokens=200)[0], skip_special_tokens=True))

Training


Base	Tesslate/OmniCoder-9B (Qwen3.5, hybrid linear-attention, 9.6B)
Method	QLoRA (4-bit NF4), LoRA rank 64
Data	cleaned code-only corpus: COBOL, x86-64 assembly, C, C++, C#
Context	up to long-form programs
Framework	Unsloth + PEFT

Formats

GGUF quants (Q8_0, Q6_K, Q4_K_M, Q2_K) for llama.cpp — use Q4_K_M or higher for reliable output; Q2_K on a 9B is best treated as experimental.
Full-precision weights available on request.

License

Apache-2.0, inherited from the base model.

Flare-9B v1.1 — because legacy code still needs to ship.

Downloads last month: 34

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

2-bit

4-bit

6-bit

8-bit

Inference Providers NEW

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

Model tree for DarkKnighToS223/FLv1.1-9B-low-level

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

Tesslate/OmniCoder-9B

Quantized

(24)

this model