Instructions to use nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF",
	filename="Qwen3.5-35B-A3B-EQ-v5-F16.gguf-00001-of-00009.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 nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF:F16

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 nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF:F16

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 nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF:F16

Use Docker

docker model run hf.co/nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF:F16

LM Studio
Jan

vLLM

How to use nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nivvis/Qwen3.5-35B-A3B-EQ-v5-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": "nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF:F16

Ollama
How to use nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF with Ollama:
```
ollama run hf.co/nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF:F16
```

Unsloth Studio

How to use nivvis/Qwen3.5-35B-A3B-EQ-v5-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 nivvis/Qwen3.5-35B-A3B-EQ-v5-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 nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF to start chatting

How to use nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF:F16

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": "nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use nivvis/Qwen3.5-35B-A3B-EQ-v5-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 nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF:F16

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 nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF:F16

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF with Docker Model Runner:
```
docker model run hf.co/nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF:F16
```

Lemonade

How to use nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF:F16

Run and chat with the model

lemonade run user.Qwen3.5-35B-A3B-EQ-v5-GGUF-F16

List all available models

lemonade list

Qwen3.5-35B-A3B-EQ-v5-GGUF

GGUF quantizations of nivvis/Qwen3.5-35B-A3B-EQ-v5 for llama.cpp, Ollama, and LM Studio.

Available quantizations

Quant	Size	BPW	Notes
F16	~65 GB	16.01	Full precision, lossless conversion
Q4_K_M	~20 GB	4.88	Best 4-bit balance, recommended for most users

Qwen3.5-35B-A3B-EQ-v5

A DPO fine-tune of Qwen3.5-35B-A3B-heretic-v2.

The tune optimized for two things:

bringing warmth, emotional intelligence, general chat improvement to Qwen 3.5 series
countering some negative tendencies of Heretic models (overwillingness to agree, be sycophantic, etc)

This is still intended as a general use model (agentic, coding, general chat). Tuning was lightly & with precision. More general benchmarks to follow.

What this model does

This model is trained to be a better conversational partner in emotionally complex situations, while maintaining base model capabilities. It:

Validates without sycophancy — empathizes with frustration without rubber-stamping bad behavior
Sets boundaries warmly — names uncomfortable truths without lecturing
Sounds human — conversational tone, not therapist-speak. better tone vs vanilla Qwen 3.5, e.g. ~~"It sounds like"~~

Key specs


Base	Qwen/Qwen3.5-35B-A3B
Parent	llmfan46/Qwen3.5-35B-A3B-heretic-v2 (decensored via MPOA+SOMA)
Fine-tune	DPO with LoRA (r=32, alpha=64)
Training data	DPO preference pairs with diverse, simulated (real-situation-based) generated dialogue

EQ-Bench 3 results

Ranked #8 on raw score* EQ-Bench 3 with only 3B active parameters — competitive with frontier models at a fraction of the compute.

#	Model	Raw Score
1	horizon-alpha	202.3
2	Kimi-K2-Instruct	202.0
3	gemini-2.5-pro-preview-06-05	200.5
4	o3	199.0
5	gpt-5	195.6
8	EQ-v5 (this model, 3B active)	193.6
10	claude-opus-4	192.6

*Table lists all models available in EQ-Bench 3 repo (so known judge, settings etc so we can be as apples to apples on raw score). Still raw score is not ideal. ELO submission pending. Better than no stats!

See the BF16 model card for full benchmarks and training details.

How to use

llama-server (OpenAI-compatible API)

llama-server \
  -m Qwen3.5-35B-A3B-EQ-v5-Q4_K_M.gguf \
  --host 0.0.0.0 --port 30000 \
  -ngl 99 --jinja

Split shards: point to the -00001-of-* file, llama.cpp auto-detects the rest.

Ollama

ollama run hf.co/nivvis/Qwen3.5-35B-A3B-EQ-v5-GGUF:Q4_K_M

Thinking mode

This model supports thinking mode. To disable (for faster, direct responses):

{"chat_template_kwargs": {"enable_thinking": false}}

Sampling recommendations

With thinking: temp=1.0, top_p=0.95, top_k=20, presence_penalty=1.5
Without thinking: temp=0.7, top_p=0.8, max_tokens=2048

Performance (Q4_K_M, single RTX 5090)

109 t/s generation
653 t/s prompt processing

Other formats

BF16 safetensors — original weights
FP8 — block-wise FP8 for vLLM/SGLang

Lineage

Qwen/Qwen3.5-35B-A3B
  → llmfan46/Qwen3.5-35B-A3B-heretic-v2 (decensored)
    → nivvis/Qwen3.5-35B-A3B-EQ-v5 (DPO for EQ)
      → this repo (GGUF quantizations)