Instructions to use Singularity87/Cityscapes-Qwen3.5-4B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Singularity87/Cityscapes-Qwen3.5-4B-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 Singularity87/Cityscapes-Qwen3.5-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Singularity87/Cityscapes-Qwen3.5-4B-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 Singularity87/Cityscapes-Qwen3.5-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Singularity87/Cityscapes-Qwen3.5-4B-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 Singularity87/Cityscapes-Qwen3.5-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Singularity87/Cityscapes-Qwen3.5-4B-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 Singularity87/Cityscapes-Qwen3.5-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Singularity87/Cityscapes-Qwen3.5-4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Singularity87/Cityscapes-Qwen3.5-4B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Singularity87/Cityscapes-Qwen3.5-4B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Singularity87/Cityscapes-Qwen3.5-4B-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": "Singularity87/Cityscapes-Qwen3.5-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Singularity87/Cityscapes-Qwen3.5-4B-GGUF:Q4_K_M

Ollama
How to use Singularity87/Cityscapes-Qwen3.5-4B-GGUF with Ollama:
```
ollama run hf.co/Singularity87/Cityscapes-Qwen3.5-4B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Singularity87/Cityscapes-Qwen3.5-4B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Singularity87/Cityscapes-Qwen3.5-4B-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": "Singularity87/Cityscapes-Qwen3.5-4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Singularity87/Cityscapes-Qwen3.5-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/Singularity87/Cityscapes-Qwen3.5-4B-GGUF:Q4_K_M
```

Lemonade

How to use Singularity87/Cityscapes-Qwen3.5-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Singularity87/Cityscapes-Qwen3.5-4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Cityscapes-Qwen3.5-4B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Singularity87/Cityscapes-Qwen3.5-4B-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 Singularity87/Cityscapes-Qwen3.5-4B-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 Singularity87/Cityscapes-Qwen3.5-4B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Singularity87/Cityscapes-Qwen3.5-4B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Singularity87/Cityscapes-Qwen3.5-4B-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 "Singularity87/Cityscapes-Qwen3.5-4B-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"

Cityscapes-Qwen3.5-4B-GGUF / release_manifest.json

Singularity87

Upload 3 files

558c397 verified about 1 month ago

Raw

History Blame Contribute Delete

4.98 kB

	{
	"schema_version": "cityscapes-huggingface-release-v1",
	"created_at": "2026-07-24T05:58:11.542574+00:00",
	"base_model": "unsloth/Qwen3.5-4B",
	"base_revision": "3764fa359b9082ea5a1e4a5e3ac3aaf6e9671636",
	"adapter": {
	"config_sha256": "31a438aaac06d47b298cb03d2f504d8df611ab19e07c8fe76a55820dfe510fcb",
	"weights_sha256": "7380b8658618b663726f987a2c26a64ba735862cc4404eeada57c214ca2bb9ba",
	"tensor_count": 688,
	"language_tensor_count": 496,
	"vision_tensor_count": 192,
	"dtype_counts": {
	"F32": 688
	}
	},
	"merge_validation": {
	"tensor_count": 738,
	"vision_tensor_count": 297,
	"language_tensor_count": 441,
	"lora_tensor_count": 0
	},
	"safetensors": {
	"directory": "Cityscapes-Qwen3.5-4B",
	"tensor_dtype_counts": {
	"BF16": 690,
	"F32": 48
	},
	"artifacts": [
	{
	"path": "model.safetensors-00001-of-00002.safetensors",
	"bytes": 5329398688,
	"sha256": "0acfb9ce10a5057b9f7ef85a83d41e3999cb608032594d7e9e5a557c8cdc4b03"
	},
	{
	"path": "model.safetensors-00002-of-00002.safetensors",
	"bytes": 3990429408,
	"sha256": "b521e3cf44161c13e23878c5b416fb1f24613d3428f2981bd440a94dc7568c1b"
	}
	]
	},
	"gguf": {
	"directory": "Cityscapes-Qwen3.5-4B-GGUF",
	"bf16_install_methods": {
	"text": "hardlink",
	"mmproj": "hardlink"
	},
	"artifacts": [
	{
	"path": "Cityscapes-Qwen3.5-4B-BF16.gguf",
	"bytes": 8665620064,
	"sha256": "46080e5b345c29a5432219d28cf08d3a50fbe22ca4b8500d5d009bd229e34e2a",
	"architecture": "qwen35",
	"general_type": "model",
	"file_type": 32,
	"tensor_count": 441,
	"tensor_type_counts": {
	"BF16": 257,
	"F32": 184
	}
	},
	{
	"path": "Cityscapes-Qwen3.5-4B-Q2_K.gguf",
	"bytes": 1959167584,
	"sha256": "ece544856792d6fe07d6969c5f8003b57efcdf29e251d09b3495581931c2494d",
	"architecture": "qwen35",
	"general_type": "model",
	"file_type": 10,
	"tensor_count": 441,
	"tensor_type_counts": {
	"F32": 184,
	"Q2_K": 181,
	"Q3_K": 42,
	"Q4_K": 33,
	"Q6_K": 1
	}
	},
	{
	"path": "Cityscapes-Qwen3.5-4B-Q4_K_M.gguf",
	"bytes": 2783446624,
	"sha256": "2e96543bf3fdfb7b4db0eb086dffe70ab2b967d0ed9b4494e4e593e7ab4e308d",
	"architecture": "qwen35",
	"general_type": "model",
	"file_type": 15,
	"tensor_count": 441,
	"tensor_type_counts": {
	"F32": 184,
	"Q4_K": 222,
	"Q6_K": 35
	}
	},
	{
	"path": "Cityscapes-Qwen3.5-4B-Q6_K.gguf",
	"bytes": 3563028064,
	"sha256": "6987d1f49ae0db02108be0d5f7ab9777653b0ff1f8e4e5adbdff6132f8f85134",
	"architecture": "qwen35",
	"general_type": "model",
	"file_type": 18,
	"tensor_count": 441,
	"tensor_type_counts": {
	"F32": 184,
	"Q6_K": 257
	}
	},
	{
	"path": "Cityscapes-Qwen3.5-4B-Q8_0.gguf",
	"bytes": 4610580064,
	"sha256": "f9e423657c2f90eb4f833f5f9e88944db7e73b5ae751ebd282e51140e2051771",
	"architecture": "qwen35",
	"general_type": "model",
	"file_type": 7,
	"tensor_count": 441,
	"tensor_type_counts": {
	"F32": 184,
	"Q8_0": 257
	}
	},
	{
	"path": "mmproj-Cityscapes-Qwen3.5-4B-BF16.gguf",
	"bytes": 675568864,
	"sha256": "9ae1a3907a5c5d2b0fe2f5c2e3c5f7e54a1ed51afb9e9fdbb7d500030dfd5e69",
	"architecture": "clip",
	"general_type": "mmproj",
	"file_type": 32,
	"tensor_count": 298,
	"tensor_type_counts": {
	"BF16": 98,
	"F32": 200
	}
	},
	{
	"path": "mmproj-Cityscapes-Qwen3.5-4B-F16.gguf",
	"bytes": 672423136,
	"sha256": "809361916bc3e683599da15d9fd485c1652458ca95e6e540a235a9ed13689c2b",
	"architecture": "clip",
	"general_type": "mmproj",
	"file_type": 1,
	"tensor_count": 298,
	"tensor_type_counts": {
	"F16": 100,
	"F32": 198
	}
	},
	{
	"path": "mmproj-Cityscapes-Qwen3.5-4B-F32.gguf",
	"bytes": 1334074592,
	"sha256": "9b29d1a9ff39866ed18126ed7afc324922c3d4af1d26c961b250c0bd4fc8b49a",
	"architecture": "clip",
	"general_type": "mmproj",
	"file_type": 0,
	"tensor_count": 298,
	"tensor_type_counts": {
	"F32": 298
	}
	}
	]
	},
	"runtime": {
	"python": "3.12.12",
	"packages": {
	"torch": "2.10.0",
	"transformers": "5.5.0",
	"peft": "0.19.1",
	"safetensors": "0.8.0",
	"unsloth": "2026.7.2"
	},
	"llama_cpp_version": "version: 9975 (a2fb27bdd)\nbuilt with GNU 11.4.0 for Linux x86_64 (Compiled by the Unsloth team)",
	"quantization_threads": 24
	}
	}