Instructions to use singularity-layer/Singularity-xMESH-0.8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use singularity-layer/Singularity-xMESH-0.8B with Transformers:

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

pipe = pipeline("image-text-to-text", model="singularity-layer/Singularity-xMESH-0.8B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("singularity-layer/Singularity-xMESH-0.8B")
model = AutoModelForMultimodalLM.from_pretrained("singularity-layer/Singularity-xMESH-0.8B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use singularity-layer/Singularity-xMESH-0.8B 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 singularity-layer/Singularity-xMESH-0.8B:BF16
# Run inference directly in the terminal:
llama cli -hf singularity-layer/Singularity-xMESH-0.8B:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf singularity-layer/Singularity-xMESH-0.8B:BF16
# Run inference directly in the terminal:
llama cli -hf singularity-layer/Singularity-xMESH-0.8B:BF16

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 singularity-layer/Singularity-xMESH-0.8B:BF16
# Run inference directly in the terminal:
./llama-cli -hf singularity-layer/Singularity-xMESH-0.8B:BF16

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 singularity-layer/Singularity-xMESH-0.8B:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf singularity-layer/Singularity-xMESH-0.8B:BF16

Use Docker

docker model run hf.co/singularity-layer/Singularity-xMESH-0.8B:BF16

Llama new
LM Studio
Jan

vLLM

How to use singularity-layer/Singularity-xMESH-0.8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "singularity-layer/Singularity-xMESH-0.8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "singularity-layer/Singularity-xMESH-0.8B",
		"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/singularity-layer/Singularity-xMESH-0.8B:BF16

SGLang

How to use singularity-layer/Singularity-xMESH-0.8B 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 "singularity-layer/Singularity-xMESH-0.8B" \
    --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": "singularity-layer/Singularity-xMESH-0.8B",
		"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 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 "singularity-layer/Singularity-xMESH-0.8B" \
        --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": "singularity-layer/Singularity-xMESH-0.8B",
		"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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use singularity-layer/Singularity-xMESH-0.8B with Ollama:
```
ollama run hf.co/singularity-layer/Singularity-xMESH-0.8B:BF16
```
Unsloth Desktop

How to use singularity-layer/Singularity-xMESH-0.8B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf singularity-layer/Singularity-xMESH-0.8B:BF16

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": "singularity-layer/Singularity-xMESH-0.8B:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use singularity-layer/Singularity-xMESH-0.8B with Docker Model Runner:
```
docker model run hf.co/singularity-layer/Singularity-xMESH-0.8B:BF16
```

Lemonade

How to use singularity-layer/Singularity-xMESH-0.8B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull singularity-layer/Singularity-xMESH-0.8B:BF16

Run and chat with the model

lemonade run user.Singularity-xMESH-0.8B-BF16

List all available models

lemonade list

Hermes Agent

How to use singularity-layer/Singularity-xMESH-0.8B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf singularity-layer/Singularity-xMESH-0.8B:BF16

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 singularity-layer/Singularity-xMESH-0.8B:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use singularity-layer/Singularity-xMESH-0.8B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf singularity-layer/Singularity-xMESH-0.8B:BF16

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 "singularity-layer/Singularity-xMESH-0.8B:BF16" \
  --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"

Singularity-xMESH-0.8B / PORTABILITY.md

ivaavi

Verify xMESH on Apple Metal and NVIDIA Vulkan GPUs

d20f5ff verified 10 days ago

preview code

Raw History Blame Contribute Delete

3.11 kB

# xMESH portability contract

Singularity Node must serve xMESH through the same `/v1/systemone` request and response contract on every supported platform.

## Runtime

- Minimum llama.cpp: `b11719` (`5aeac37a35b44fde4bdffaec9159f2fcb253b622`).
- Context: 2,048 tokens per request.
- Physical batch: 2,048 tokens. The llama.cpp default of 512 rejects normal multi-field requests.
- Default concurrency: one slot. Higher concurrency requires a platform-specific canary.
- GPU offload (`-ngl 99`) on accelerators that passed frozen-suite decision parity against CPU: Apple Metal (959/960 decisions, one near-tie) and NVIDIA through the Vulkan build (960/960). Singularity Node v1.10.4+ selects this itself. Every other setup runs on CPU (`-ngl 0`). Evidence: `ACCELERATOR_PARITY.json`.
- System memory: 8 GB minimum; 16 GB recommended.

## Artifacts

| Artifact | Bytes | SHA-256 | Use |
| --- | ---: | --- | --- |
| `Singularity-xMESH-0.8B-BF16.gguf` | 1,571,529,600 | `9f4c08f19c4d203059bc74ed2754e800ec472d7276d8ddb2321480e86d392fff` | Universal Node artifact |
| `Singularity-xMESH-0.8B-Q8_0.gguf` | 841,069,440 | `41b36270b67f6c595e98cf4f29d6a0d13f0c19daa37b75741cd8296e2729fd75` | Accelerated runtimes only |

Q8 passes the full Metal decision-parity suite but crashes in llama.cpp `b11719` during CPU initialization. Q4_K_M loads but changes 16 of 960 frozen decisions, so it is not a release artifact.

## Release matrix

| Surface | Target | Artifact | Status |
| --- | --- | --- | --- |
| Desktop | macOS Apple silicon | BF16 | Full Metal offload: 959/960 frozen-suite decisions match CPU; packaged-app Run Locally and Grid serving canaries passed (Desktop 1.10.7) |
| Desktop / Node | Windows x64 CPU | BF16 | Production Vulkan distribution with `-ngl 0` passed 9/9 decisions |
| Node CLI | Linux x64 CPU | BF16 | Production Vulkan distribution with `-ngl 0` passed 9/9 decisions on Ubuntu 24.04 |
| Node CLI | Linux ARM64 CPU | BF16 | CPU load and real decision canary passed in Ubuntu 24.04 ARM64 |
| Node CLI | Linux x64 NVIDIA GPU | BF16 | Production Vulkan distribution with `-ngl 99` on an RTX A4000: 960/960 frozen-suite decisions match CPU, 0.31 s median per request |

The desktop release workflow does not currently publish Linux or Intel Mac packages. The Node CLI covers Linux; Intel Mac desktop support requires a separate release target.

The official Linux llama.cpp archive links `libgomp.so.1`. Minimal Ubuntu images must install the standard `libgomp1` package before `sgl setup`; normal desktop/server distributions often already include it. The provisioner must surface this exact prerequisite when the staged binary fails its launch check.

## Quality gates

- Frozen x402 export parity: 80 cases and 960 decisions.
- Official typed-decisions boundary suite: 400 cases and 2,000 decisions.
- Option-order robustness: 600 choice decisions.
- Runtime integrity: exact artifact and llama.cpp archive hashes.
- Platform canary: load, health, real `/v1/systemone` request, expected answer, and clean shutdown.

See `GGUF_VALIDATION.json` for measurements and rejected artifact evidence.

	# xMESH portability contract

	Singularity Node must serve xMESH through the same `/v1/systemone` request and response contract on every supported platform.

	## Runtime

	- Minimum llama.cpp: `b11719` (`5aeac37a35b44fde4bdffaec9159f2fcb253b622`).
	- Context: 2,048 tokens per request.
	- Physical batch: 2,048 tokens. The llama.cpp default of 512 rejects normal multi-field requests.
	- Default concurrency: one slot. Higher concurrency requires a platform-specific canary.
	- GPU offload (`-ngl 99`) on accelerators that passed frozen-suite decision parity against CPU: Apple Metal (959/960 decisions, one near-tie) and NVIDIA through the Vulkan build (960/960). Singularity Node v1.10.4+ selects this itself. Every other setup runs on CPU (`-ngl 0`). Evidence: `ACCELERATOR_PARITY.json`.
	- System memory: 8 GB minimum; 16 GB recommended.

	## Artifacts

	\| Artifact \| Bytes \| SHA-256 \| Use \|
	\| --- \| ---: \| --- \| --- \|
	\| `Singularity-xMESH-0.8B-BF16.gguf` \| 1,571,529,600 \| `9f4c08f19c4d203059bc74ed2754e800ec472d7276d8ddb2321480e86d392fff` \| Universal Node artifact \|
	\| `Singularity-xMESH-0.8B-Q8_0.gguf` \| 841,069,440 \| `41b36270b67f6c595e98cf4f29d6a0d13f0c19daa37b75741cd8296e2729fd75` \| Accelerated runtimes only \|

	Q8 passes the full Metal decision-parity suite but crashes in llama.cpp `b11719` during CPU initialization. Q4_K_M loads but changes 16 of 960 frozen decisions, so it is not a release artifact.

	## Release matrix

	\| Surface \| Target \| Artifact \| Status \|
	\| --- \| --- \| --- \| --- \|
	\| Desktop \| macOS Apple silicon \| BF16 \| Full Metal offload: 959/960 frozen-suite decisions match CPU; packaged-app Run Locally and Grid serving canaries passed (Desktop 1.10.7) \|
	\| Desktop / Node \| Windows x64 CPU \| BF16 \| Production Vulkan distribution with `-ngl 0` passed 9/9 decisions \|
	\| Node CLI \| Linux x64 CPU \| BF16 \| Production Vulkan distribution with `-ngl 0` passed 9/9 decisions on Ubuntu 24.04 \|
	\| Node CLI \| Linux ARM64 CPU \| BF16 \| CPU load and real decision canary passed in Ubuntu 24.04 ARM64 \|
	\| Node CLI \| Linux x64 NVIDIA GPU \| BF16 \| Production Vulkan distribution with `-ngl 99` on an RTX A4000: 960/960 frozen-suite decisions match CPU, 0.31 s median per request \|

	The desktop release workflow does not currently publish Linux or Intel Mac packages. The Node CLI covers Linux; Intel Mac desktop support requires a separate release target.

	The official Linux llama.cpp archive links `libgomp.so.1`. Minimal Ubuntu images must install the standard `libgomp1` package before `sgl setup`; normal desktop/server distributions often already include it. The provisioner must surface this exact prerequisite when the staged binary fails its launch check.

	## Quality gates

	- Frozen x402 export parity: 80 cases and 960 decisions.
	- Official typed-decisions boundary suite: 400 cases and 2,000 decisions.
	- Option-order robustness: 600 choice decisions.
	- Runtime integrity: exact artifact and llama.cpp archive hashes.
	- Platform canary: load, health, real `/v1/systemone` request, expected answer, and clean shutdown.

	See `GGUF_VALIDATION.json` for measurements and rejected artifact evidence.