Instructions to use hardin/Webcoda-AI-35B-A3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hardin/Webcoda-AI-35B-A3B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="hardin/Webcoda-AI-35B-A3B-GGUF",
	filename="Webcoda-AI-35B-A3B-Q6_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 hardin/Webcoda-AI-35B-A3B-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 hardin/Webcoda-AI-35B-A3B-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf hardin/Webcoda-AI-35B-A3B-GGUF:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf hardin/Webcoda-AI-35B-A3B-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf hardin/Webcoda-AI-35B-A3B-GGUF:Q6_K

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 hardin/Webcoda-AI-35B-A3B-GGUF:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf hardin/Webcoda-AI-35B-A3B-GGUF:Q6_K

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 hardin/Webcoda-AI-35B-A3B-GGUF:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf hardin/Webcoda-AI-35B-A3B-GGUF:Q6_K

Use Docker

docker model run hf.co/hardin/Webcoda-AI-35B-A3B-GGUF:Q6_K

LM Studio
Jan
Ollama
How to use hardin/Webcoda-AI-35B-A3B-GGUF with Ollama:
```
ollama run hf.co/hardin/Webcoda-AI-35B-A3B-GGUF:Q6_K
```

Unsloth Studio

How to use hardin/Webcoda-AI-35B-A3B-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 hardin/Webcoda-AI-35B-A3B-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 hardin/Webcoda-AI-35B-A3B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for hardin/Webcoda-AI-35B-A3B-GGUF to start chatting

How to use hardin/Webcoda-AI-35B-A3B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hardin/Webcoda-AI-35B-A3B-GGUF:Q6_K

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": "hardin/Webcoda-AI-35B-A3B-GGUF:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use hardin/Webcoda-AI-35B-A3B-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 hardin/Webcoda-AI-35B-A3B-GGUF:Q6_K

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 hardin/Webcoda-AI-35B-A3B-GGUF:Q6_K

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use hardin/Webcoda-AI-35B-A3B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hardin/Webcoda-AI-35B-A3B-GGUF:Q6_K

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 "hardin/Webcoda-AI-35B-A3B-GGUF:Q6_K" \
  --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 hardin/Webcoda-AI-35B-A3B-GGUF with Docker Model Runner:
```
docker model run hf.co/hardin/Webcoda-AI-35B-A3B-GGUF:Q6_K
```

Lemonade

How to use hardin/Webcoda-AI-35B-A3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull hardin/Webcoda-AI-35B-A3B-GGUF:Q6_K

Run and chat with the model

lemonade run user.Webcoda-AI-35B-A3B-GGUF-Q6_K

List all available models

lemonade list

Webcoda AI — 35B-A3B (Q6_K GGUF)

Webcoda AI is a knowledge assistant fine-tuned from unsloth/Qwen3.6-35B-A3B (a Mixture-of-Experts model, 256 experts / ~3B active) to answer questions about Webcoda, a Sydney-based digital agency. This is the highest-quality model in the Webcoda AI family — it passed 6/6 on the factual + identity validation gate.

Run it (llama.cpp / LM Studio / Ollama)

One universal file — runs on Mac (Metal), AMD (Vulkan/ROCm), and NVIDIA (CUDA), or CPU. Requires a recent llama.cpp build (linear-attention qwen3_5_moe support).

hf download hardin/Webcoda-AI-35B-A3B-GGUF Webcoda-AI-35B-A3B-Q6_K.gguf --local-dir .
llama-server --model Webcoda-AI-35B-A3B-Q6_K.gguf --jinja --ctx-size 8192 --n-gpu-layers 999

Identity is baked in — a bare "What is your name?" answers "Webcoda AI" with no system prompt needed.

Model details

Base: unsloth/Qwen3.6-35B-A3B (Qwen3_5MoeForConditionalGeneration)
Fine-tune: bf16 LoRA, r=128, on the attention + MoE expert projections (17.5% of params trainable), merged to 16-bit then quantized to Q6_K (~28.5 GB).
Text-only: the base model's vision tower and MTP (nextn) speculative head were removed during GGUF export; standard autoregressive inference is unaffected.
Tokenizer: PreTrainedTokenizerFast (repacked from the base's newer backend).

Family

hardin/Webcoda-AI-14B-GGUF — smaller/faster (dense)
hardin/Webcoda-AI-27B-GGUF — dense mid-size
hardin/Webcoda-AI-35B-A3B-GGUF — this (MoE, best accuracy, ~3B active params → fast)

Downloads last month: 139

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

6-bit

Inference Providers NEW

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

Model tree for hardin/Webcoda-AI-35B-A3B-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

unsloth/Qwen3.6-35B-A3B

Quantized

(3)

this model