Instructions to use pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-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 pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-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 pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-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 pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-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 pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF:Q4_K_M

Use Docker

docker model run hf.co/pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-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": "pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF:Q4_K_M

SGLang

How to use pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF with Ollama:
```
ollama run hf.co/pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF:Q4_K_M
```
Unsloth Desktop

How to use pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-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": "pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF with Docker Model Runner:
```
docker model run hf.co/pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF:Q4_K_M
```

Lemonade

How to use pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen-35B-A3B-SignOfFour-Coder-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-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 pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-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 pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-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 "pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-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"

Qwen-35B-A3B-SignOfFour-Coder-GGUF / README.md

pragmaticcs

Update README.md

fdf2cc9 about 1 month ago

preview code

Raw History Blame

8.69 kB

	---
	base_model:
	- Jackrong/Qwopus3.6-35B-A3B-Coder
	- ornith-ai/Ornith-1.5-35B-A3B
	- Kwaipilot/KAT-Coder-V2.5-Dev
	- Qwen/Qwen-AgentWorld-35B-A3B
	base_model_relation: merge
	library_name: transformers
	tags:
	- merge
	- ties
	- dare
	- moe
	- qwen
	- qwen3.5
	- qwen3.6
	- causal-lm
	- deltanet
	- agentic
	- reasoning
	- code
	license: apache-2.0
	language:
	- en
	- zh
	pipeline_tag: text-generation
	model_type: qwen3_5_moe
	---

	<div align="center">

	[![License](https://img.shields.io/badge/License-Apache%202.0-6E56CF?style=for-the-badge)](https://opensource.org/licenses/Apache-2.0)
	[![Library](https://img.shields.io/badge/Library-transformers-FFD21E?style=for-the-badge&logo=huggingface&logoColor=black)](https://github.com/huggingface/transformers)
	[![Merge Method](https://img.shields.io/badge/Merge%20Method-DARE--TIES-27AE60?style=for-the-badge)](#merge-methodology)

	[![Architecture](https://img.shields.io/badge/Architecture-Qwen%2035B--A3B%20MoE-2D9CDB?style=for-the-badge)](#architectural-specifications)
	[![Experts](https://img.shields.io/badge/Routed%20Experts-256-EB5757?style=for-the-badge)](#architectural-specifications)
	[![Layers](https://img.shields.io/badge/Decoder%20Layers-40-F2994A?style=for-the-badge)](#architectural-specifications)

	</div>

	A four-way MoE merge of the Qwen 35B-A3B architecture, fusing task vectors from three specialized fine-tunes into a base anchor via DARE-TIES with sinusoidal depth modulation.

	> [!IMPORTANT]
	> Designed specifically to consolidate software engineering, code synthesis, and agentic tool execution capabilities. Multimodal vision weights and Multi-Token Prediction (MTP) heads were stripped to reduce VRAM footprint and maximize throughput during coding tasks.

	---

	### Contents

	- [Architectural Specifications](#architectural-specifications)
	- [Composition](#composition)
	- [Merge Methodology](#merge-methodology)
	- [Layer-Stratified Policies](#layer-stratified-policies)
	- [Chat Template](#chat-template)
	- [Generation Parameters](#recommended-generation-parameters)
	- [How to Use](#how-to-use)
	- [Lineage](#lineage)
	- [References](#citation--references)

	---

	## Architectural Specifications

	\| Spec \| Value \|
	\| :--- \| :---: \|
	\| Total parameters \| 35B \|
	\| Active parameters / token \| 3B \|
	\| Decoder layers \| 40 \|
	\| Routed experts \| 256 \|
	\| Shared experts \| 1 \|
	\| Attention \| Gated DeltaNet hybrid linear attention \|
	\| Merge algorithm \| DARE-TIES + sine depth scaling \|

	## Composition

	`Jackrong/Qwopus3.6-35B-A3B-Coder` serves as the base anchor (W₀); the remaining three models contribute task vectors at the listed weights.

	\| Model \| Role \| Task Weight (α) \|
	\| :--- \| :--- \| :---: \|
	\| [Jackrong/Qwopus3.6-35B-A3B-Coder](https://huggingface.co/Jackrong/Qwopus3.6-35B-A3B-Coder) \| Base anchor (W₀) \| 1.00 \|
	\| [ornith-ai/Ornith-1.5-35B-A3B](https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B) \| Donor (D₁) \| 0.30 \|
	\| [Kwaipilot/KAT-Coder-V2.5-Dev](https://huggingface.co/Kwaipilot/KAT-Coder-V2.5-Dev) \| Donor (D₂) \| 0.25 \|
	\| [Qwen/Qwen-AgentWorld-35B-A3B](https://huggingface.co/Qwen/Qwen-AgentWorld-35B-A3B) \| Donor (D₃) \| 0.20 \|

	---

	## Merge Methodology

	For each floating-point parameter, a task delta is computed per donor \$k\$:

	$$
	\Delta_k = D_k - W_0
	$$

	DARE pruning. A Bernoulli mask at retention density \$p\$ zeroes out low-magnitude updates; surviving values are rescaled by \$p^{-1}\$:

	$$
	\tilde{\Delta}_k = \frac{1}{p} \left(\Delta_k \odot M_k\right), \quad M_k \sim \text{Bernoulli}(p)
	$$

	TIES sign election. A consensus sign \$\Gamma\$ is computed via weighted vote across donors, and any donor update conflicting with it is dropped before averaging:

	$$
	\Gamma = \operatorname{sgn}\left(\sum_{k=1}^K \alpha_k \tilde{\Delta}_k\right)
	$$

	$$
	\Delta_{\text{TIES}} = \frac{\sum_{k=1}^K \alpha_k \tilde{\Delta}_k \odot \mathbb{I}\left(\operatorname{sgn}(\tilde{\Delta}_k) = \Gamma\right)}{\sum_{k=1}^K \alpha_k \cdot \mathbb{I}\left(\operatorname{sgn}(\tilde{\Delta}_k) = \Gamma\right) + \epsilon}
	$$

	Depth-scaled reconstruction. The merged weight is reconstructed as:

	$$
	W_{\text{final}} = W_0 + \lambda(l) \cdot \Delta_{\text{TIES}}
	$$

	where the layer scaling factor \$\lambda(l)\$ across decoder layer index \$l \in [0, 39]\$ is defined as:

	$$
	\lambda(l) = \beta \cdot \left(0.5 + 0.5 \sin\left(\pi \frac{l}{39}\right)\right)
	$$

	This keeps input/output projections closer to the base and applies the strongest task transfer to middle layers \$(l \in [12, 28])\$.

	---

	## Layer-Stratified Policies

	\| Parameter Group \| Match Substring \| Policy \| Density (p) \| Base Scale (β) \|
	\| :--- \| :--- \| :---: \| :---: \| :---: \|
	\| Embeddings / LM head \| `embed_tokens`, `lm_head` \| Linear \| — \| 1.00 \|
	\| Norms / biases \| `norm`, `bias`, 1D tensors \| Linear \| — \| 1.00 \|
	\| DeltaNet recurrent state \| `a_log`, `dt_bias`, `conv1d` \| Linear \| — \| 1.00 \|
	\| MoE router gate \| `mlp.gate.weight`, `block_sparse_moe.gate` \| Linear \| — \| 1.00 \|
	\| MoE shared expert \| `shared_expert` \| DARE‑TIES \| 0.70 \| 0.60 \|
	\| Attention projections \| `attn`, `rotary`, `in_proj`, `out_proj`, `x_proj` \| DARE‑TIES \| 0.75 \| 0.60 \|
	\| Routed experts (×256) \| `experts`, `mlp` \| DARE‑TIES \| 0.65 \| 0.55 \|

	- Router protection: Gate weights use linear interpolation (~57% base, ~43% donors) rather than DARE to avoid destabilizing expert routing.
	- DeltaNet stability: Recurrent state kernels are excluded from DARE to prevent divergence in the linear-attention state space.
	- MTP removed: Multi-token-prediction heads beyond the 40 primary decoder blocks were stripped for standard CausalLM inference.

	---

	## Chat Template

	This model uses the [Improved Chat Template for Qwen 3.x by Olivia Rossi](https://huggingface.co/OliviaRossi/Improved-Chat-Template-for-Qwen-3.x) to support multi-tier Chain-of-Thought (CoT) reasoning, dual-format agentic tool execution, automatic error-recovery heuristics, and strict token-waste elimination.

	---

	## Recommended Generation Parameters

	For code generation and agentic task trajectories, avoid high temperatures to maintain routing stability and syntax validity.

	\| Parameter \| Coding / Terminal Agent \| Creative Reasoning \|
	\| :--- \| :---: \| :---: \|
	\| Temperature \| `0.6` \| `1.0` \|
	\| Top-P \| `0.95` \| `0.95` \|
	\| Min-P \| `0.0` \| `0.01` \|
	\| Repetition Penalty \| `off` \| `1.05` \|

	---

	## How to Use

	### Transformers

	```python
	import torch
	from transformers import AutoModelForCausalLM, AutoTokenizer

	model_id = "pragmaticcs/SignOfFour"

	tokenizer = AutoTokenizer.from_pretrained(model_id)
	model = AutoModelForCausalLM.from_pretrained(
	model_id,
	torch_dtype=torch.bfloat16,
	device_map="auto",
	)

	messages = [
	{"role": "system", "content": "You are a precise agentic software engineer. Solve problems concisely."},
	{"role": "user", "content": "Write an asynchronous Python queue consumer with retry backoff."}
	]

	inputs = tokenizer.apply_chat_template(
	messages, add_generation_prompt=True, return_tensors="pt"
	).to(model.device)

	output = model.generate(
	inputs,
	max_new_tokens=1024,
	temperature=0.6,
	top_p=0.95,
	min_p=0.01,
	do_sample=True,
	)

	print(tokenizer.decode(output[0][inputs.shape[-1]:], skip_special_tokens=True))
	```

	---

	## Lineage

	```
	Qwen/Qwen3.6-35B-A3B
	└── pragmaticcs/SignOfFour
	├── base: Jackrong/Qwopus3.6-35B-A3B-Coder
	├── donor: ornith-ai/Ornith-1.5-35B-A3B
	├── donor: Kwaipilot/KAT-Coder-V2.5-Dev
	└── donor: Qwen/Qwen-AgentWorld-35B-A3B
	```

	---

	## Citation & References

	- [Jackrong/Qwopus3.6-35B-A3B-Coder](https://huggingface.co/Jackrong/Qwopus3.6-35B-A3B-Coder)
	- [ornith-ai/Ornith-1.5-35B-A3B](https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B)
	- [Kwaipilot/KAT-Coder-V2.5-Dev](https://huggingface.co/Kwaipilot/KAT-Coder-V2.5-Dev)
	- [Qwen/Qwen-AgentWorld-35B-A3B](https://huggingface.co/Qwen/Qwen-AgentWorld-35B-A3B)
	- [Improved Chat Template for Qwen 3.x](https://huggingface.co/OliviaRossi/Improved-Chat-Template-for-Qwen-3.x)

	```bibtex
	@inproceedings{yu2024dare,
	title={Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch},
	author={Yu, Le and Yu, Bowen and Yu, Haiyang and Huang, Fei and Li, Yongbin},
	booktitle={International Conference on Machine Learning (ICML)},
	year={2024}
	}

	@inproceedings{yadav2023ties,
	title={Resolving Interference When Merging Models},
	author={Yadav, Prateek and Tam, Derek and Choshen, Leshem and Raffel, Colin and Bansal, Mohit},
	booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
	year={2023}
	}
	```