Instructions to use Romarchive/Qwen3.5-2B-Base-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Romarchive/Qwen3.5-2B-Base-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Romarchive/Qwen3.5-2B-Base-GGUF",
	filename="Qwen3.5 2B Base IQ3_M (2026)[Romarchive].gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Romarchive/Qwen3.5-2B-Base-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Romarchive/Qwen3.5-2B-Base-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Romarchive/Qwen3.5-2B-Base-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Romarchive/Qwen3.5-2B-Base-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Romarchive/Qwen3.5-2B-Base-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 Romarchive/Qwen3.5-2B-Base-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Romarchive/Qwen3.5-2B-Base-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 Romarchive/Qwen3.5-2B-Base-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Romarchive/Qwen3.5-2B-Base-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Romarchive/Qwen3.5-2B-Base-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Romarchive/Qwen3.5-2B-Base-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Romarchive/Qwen3.5-2B-Base-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": "Romarchive/Qwen3.5-2B-Base-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Romarchive/Qwen3.5-2B-Base-GGUF:Q4_K_M

Ollama
How to use Romarchive/Qwen3.5-2B-Base-GGUF with Ollama:
```
ollama run hf.co/Romarchive/Qwen3.5-2B-Base-GGUF:Q4_K_M
```

Unsloth Studio new

How to use Romarchive/Qwen3.5-2B-Base-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 Romarchive/Qwen3.5-2B-Base-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 Romarchive/Qwen3.5-2B-Base-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Romarchive/Qwen3.5-2B-Base-GGUF to start chatting

Pi new

How to use Romarchive/Qwen3.5-2B-Base-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Romarchive/Qwen3.5-2B-Base-GGUF: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": "Romarchive/Qwen3.5-2B-Base-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Romarchive/Qwen3.5-2B-Base-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 Romarchive/Qwen3.5-2B-Base-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 Romarchive/Qwen3.5-2B-Base-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Romarchive/Qwen3.5-2B-Base-GGUF with Docker Model Runner:
```
docker model run hf.co/Romarchive/Qwen3.5-2B-Base-GGUF:Q4_K_M
```

Lemonade

How to use Romarchive/Qwen3.5-2B-Base-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Romarchive/Qwen3.5-2B-Base-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-2B-Base-GGUF-Q4_K_M

List all available models

lemonade list

Quantized at Romarchive

Qwen3.5-2B-Base

This repository contains model weights and configuration files for the pre-trained only model in the Hugging Face Transformers format.

These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, etc.

The intended use cases are fine-tuning, in-context learning experiments, and other research or development purposes, not direct interaction. However, the control tokens, e.g., <|im_start|> and <|im_end|> were trained to allow efficient LoRA-style PEFT with the official chat template, mitigating the need to finetune embeddings, a significant optimization given Qwen3.5's larger vocabulary.

Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency.

Qwen3.5 Highlights

Qwen3.5 features the following enhancement:

Unified Vision-Language Foundation: Early fusion training on multimodal tokens achieves cross-generational parity with Qwen3 and outperforms Qwen3-VL models across reasoning, coding, agents, and visual understanding benchmarks.
Efficient Hybrid Architecture: Gated Delta Networks combined with sparse Mixture-of-Experts deliver high-throughput inference with minimal latency and cost overhead.
Scalable RL Generalization: Reinforcement learning scaled across million-agent environments with progressively complex task distributions for robust real-world adaptability.
Global Linguistic Coverage: Expanded support to 201 languages and dialects, enabling inclusive, worldwide deployment with nuanced cultural and regional understanding.
Next-Generation Training Infrastructure: Near-100% multimodal training efficiency compared to text-only training and asynchronous RL frameworks supporting massive-scale agent scaffolds and environment orchestration.

For more details, please refer to our blog post Qwen3.5.

Model Overview

Type: Causal Language Model with Vision Encoder
Training Stage: Pre-training & Post-training
Language Model
- Number of Parameters: 2B
- Hidden Dimension: 2048
- Token Embedding: 248320 (Padded)
- Number of Layers: 24
- Hidden Layout: 6 × (3 × (Gated DeltaNet → FFN) → 1 × (Gated Attention → FFN))
- Gated DeltaNet:
  - Number of Linear Attention Heads: 16 for V and 16 for QK
  - Head Dimension: 128
- Gated Attention:
  - Number of Attention Heads: 8 for Q and 2 for KV
  - Head Dimension: 256
  - Rotary Position Embedding Dimension: 64
- Feed Forward Network:
  - Intermediate Dimension: 6144
- LM Output: 248320 (Tied to token embedding)
- MTP: trained with multi-steps
Context Length: 262,144 natively and extensible up to 1,010,000 tokens.

Citation

If you find our work helpful, feel free to give us a cite.

@misc{qwen3.5,
    title  = {{Qwen3.5}: Towards Native Multimodal Agents},
    author = {{Qwen Team}},
    month  = {February},
    year   = {2026},
    url    = {https://qwen.ai/blog?id=qwen3.5}
}

Downloads last month: 61

GGUF

Model size

2B params

Architecture

qwen35

Hardware compatibility

1-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for Romarchive/Qwen3.5-2B-Base-GGUF

Base model

Qwen/Qwen3.5-2B-Base

Quantized

(22)

this model