Instructions to use el4/SIQ-1-35B-APEX-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use el4/SIQ-1-35B-APEX-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="el4/SIQ-1-35B-APEX-GGUF",
	filename="SIQ-1-35B-APEX-I-BALANCED-PATCHED.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use el4/SIQ-1-35B-APEX-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 el4/SIQ-1-35B-APEX-GGUF
# Run inference directly in the terminal:
llama cli -hf el4/SIQ-1-35B-APEX-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf el4/SIQ-1-35B-APEX-GGUF
# Run inference directly in the terminal:
llama cli -hf el4/SIQ-1-35B-APEX-GGUF

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 el4/SIQ-1-35B-APEX-GGUF
# Run inference directly in the terminal:
./llama-cli -hf el4/SIQ-1-35B-APEX-GGUF

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 el4/SIQ-1-35B-APEX-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf el4/SIQ-1-35B-APEX-GGUF

Use Docker

docker model run hf.co/el4/SIQ-1-35B-APEX-GGUF

LM Studio
Jan

vLLM

How to use el4/SIQ-1-35B-APEX-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "el4/SIQ-1-35B-APEX-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "el4/SIQ-1-35B-APEX-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/el4/SIQ-1-35B-APEX-GGUF

Ollama
How to use el4/SIQ-1-35B-APEX-GGUF with Ollama:
```
ollama run hf.co/el4/SIQ-1-35B-APEX-GGUF
```

Unsloth Studio

How to use el4/SIQ-1-35B-APEX-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 el4/SIQ-1-35B-APEX-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 el4/SIQ-1-35B-APEX-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for el4/SIQ-1-35B-APEX-GGUF to start chatting

How to use el4/SIQ-1-35B-APEX-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf el4/SIQ-1-35B-APEX-GGUF

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": "el4/SIQ-1-35B-APEX-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use el4/SIQ-1-35B-APEX-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 el4/SIQ-1-35B-APEX-GGUF

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 el4/SIQ-1-35B-APEX-GGUF

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use el4/SIQ-1-35B-APEX-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf el4/SIQ-1-35B-APEX-GGUF

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 "el4/SIQ-1-35B-APEX-GGUF" \
  --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 el4/SIQ-1-35B-APEX-GGUF with Docker Model Runner:
```
docker model run hf.co/el4/SIQ-1-35B-APEX-GGUF
```

Lemonade

How to use el4/SIQ-1-35B-APEX-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull el4/SIQ-1-35B-APEX-GGUF

Run and chat with the model

lemonade run user.SIQ-1-35B-APEX-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Please check out my refined quant of this model!

https://huggingface.co/el4/SIQ-1-35B-OPAL-GGUF

Please used the patched versions- the original had a metadata bug that I had to manually fix also there is no MTP support

SIQ-1-35B - APEX Quantized (GGUF)

This repository contains GGUF quants of AlexWortega/SIQ-1-35B using the APEX quantization method developed by LocalAI.

These quants are specifically optimized to provide superior perplexity and benchmark scores at lower file sizes compared to standard GGUF quantization methods (like Q4_K_M or Q5_K_M).

About APEX Quantization

APEX (Adaptive Precision EXtension) uses a custom layer-wise bit allocation strategy. Instead of applying a uniform bit-depth across the entire model, APEX analyzes the sensitivity of each layer and assigns higher precision to critical layers while aggressively compressing less sensitive ones.

Result: You get the intelligence of a Q6_K model at the file size of a Q4_K model, making it perfect for running large models on consumer hardware with partial GPU offloading.

📊 File Guide & Hardware Recommendations

SIQ-1-35B consists of 40 transformer layers. Choose the file that best fits your VRAM and System RAM constraints.

Filename	Size	Quant Profile	Best For	GPU Offload (12GB VRAM)	GPU Offload (24GB VRAM)
`SIQ-1-35B-APEX-I-Quality.gguf`	21.3 GB	I-Quality	Max intelligence, agentic coding, complex reasoning.	~28 Layers	~36 Layers
`SIQ-1-35B-APEX-I-Balanced.gguf`	23.6 GB	I-Balanced	Best balance of speed and high-fidelity output.	~26 Layers	~34 Layers
`SIQ-1-35B-APEX-I-Compact.gguf`	16.1 GB	I-Compact	Fast generation, lower system RAM limits.	~34 Layers	All 40 Layers

Note: "GPU Offload" estimates assume standard FP16 KV Cache. If using Q8_0 or Q4_0 KV Cache quantization, you can fit slightly more layers on the GPU.

🚀 Usage Instructions

LM Studio

Download the .gguf file that matches your hardware.
Import the file into LM Studio.
In the right-hand settings panel, set GPU Offload to the maximum recommended layers for your VRAM (see table above).
Adjust the Context Length as needed (Tested up to 160k with YaRN scaling).

llama.cpp / ik_llama.cpp (CLI)

./llama-server -m SIQ-1-35B-APEX-I-Quality.gguf -ngl 28 -c 16384 --cache-type-k q8_0 --cache-type-v q8_0

(Adjust -ngl based on your VRAM. Use --cache-type to reduce VRAM usage for large context windows).

📈 Performance & Quality

APEX I-Quality significantly outperforms standard quants of similar size. Based on core metrics for the 35B architecture:

Perplexity: 6.552 (Matches or beats standard Q5_K_M and Q6_K)
MMLU: 41.4%
ARC: 57.9%
TQA: 38.4%

Credits & Acknowledgments

Base Model: AlexWortega/SIQ-1-35B by Alex Wortega.
Quantization Method: apex-quant by LocalAI.
GGUF Ecosystem: llama.cpp by Georgi Gerganov and contributors.

📄 License

This quantization inherits the license of the base model. Please refer to the original model card for specific licensing details.

Downloads last month: 5,727

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for el4/SIQ-1-35B-APEX-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

AlexWortega/SIQ-1-35B

Quantized

(4)

this model

Collection including el4/SIQ-1-35B-APEX-GGUF

APEX

Collection

1 item • Updated 5 days ago • 1