Instructions to use RalphLabsAI/ralph-crowns with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use RalphLabsAI/ralph-crowns 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 RalphLabsAI/ralph-crowns
# Run inference directly in the terminal:
llama cli -hf RalphLabsAI/ralph-crowns

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RalphLabsAI/ralph-crowns
# Run inference directly in the terminal:
llama cli -hf RalphLabsAI/ralph-crowns

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 RalphLabsAI/ralph-crowns
# Run inference directly in the terminal:
./llama-cli -hf RalphLabsAI/ralph-crowns

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 RalphLabsAI/ralph-crowns
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RalphLabsAI/ralph-crowns

Use Docker

docker model run hf.co/RalphLabsAI/ralph-crowns

Llama new
LM Studio
Jan

vLLM

How to use RalphLabsAI/ralph-crowns with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RalphLabsAI/ralph-crowns"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RalphLabsAI/ralph-crowns",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RalphLabsAI/ralph-crowns

Ollama
How to use RalphLabsAI/ralph-crowns with Ollama:
```
ollama run hf.co/RalphLabsAI/ralph-crowns
```
Unsloth Desktop
Docker Model Runner
How to use RalphLabsAI/ralph-crowns with Docker Model Runner:
```
docker model run hf.co/RalphLabsAI/ralph-crowns
```

Lemonade

How to use RalphLabsAI/ralph-crowns with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RalphLabsAI/ralph-crowns

Run and chat with the model

lemonade run user.ralph-crowns-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

bitzic commited on Aug 31

Commit

d7f9d0d

verified ·

1 Parent(s): 7e27d77

crowns as of round 5

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ changes hands, the file here changes with it.
 | file | tier | bits/weight | size | retention | round | scored artifact |
 |---|---|---|---|---|---|---|
 | `ralph-qwen3-8b-binary.gguf` | binary | 1.1477 | 1.91 GB | 0.1886 | 3 | [`tensor-tailor/ralph-qwen3-8b-binary`](https://huggingface.co/tensor-tailor/ralph-qwen3-8b-binary) @`4da9ef27964f` |
-| `ralph-qwen3-8b-ternary.gguf` | ternary | 1.6095 | 2.33 GB | 0.180233 | 1 | [`crazy-m1ner/ralph-qwen3-8b-ternary`](https://huggingface.co/crazy-m1ner/ralph-qwen3-8b-ternary) @`main` |
 | `ralph-qwen3-8b-sub2.gguf` | sub2 | 2.1587 | 2.82 GB | 0.227453 | 3 | [`tensor-tailor/ralph-qwen3-8b-sub2-r3`](https://huggingface.co/tensor-tailor/ralph-qwen3-8b-sub2-r3) @`fb4ee26b2c43` |
 | `ralph-qwen3-8b-sub4.gguf` | sub4 | 4.0 | 4.61 GB | 0.302385 | 1 | [`andreas11112/qwen3-8b-sn40-sub4`](https://huggingface.co/andreas11112/qwen3-8b-sn40-sub4) @`8c8cfa61be18` |
@@ -26,7 +26,7 @@ than its average. It is a compression-fidelity measure. **It is not a capability
 high retention does not by itself mean a model is good at anything in particular.
 Round record, with the exam, every per-sample measurement and the crown decision:
-https://huggingface.co/datasets/RalphLabsAI/ralph-v2-rounds/resolve/main/rounds/round-00000003-4d84770bd076e652.json
 ## Provenance

 | file | tier | bits/weight | size | retention | round | scored artifact |
 |---|---|---|---|---|---|---|
 | `ralph-qwen3-8b-binary.gguf` | binary | 1.1477 | 1.91 GB | 0.1886 | 3 | [`tensor-tailor/ralph-qwen3-8b-binary`](https://huggingface.co/tensor-tailor/ralph-qwen3-8b-binary) @`4da9ef27964f` |
+| `ralph-qwen3-8b-ternary.gguf` | ternary | 1.714 | 2.46 GB | 0.253732 | 5 | [`tensor-tailor/ralph-qwen3-8b-ternary-r5`](https://huggingface.co/tensor-tailor/ralph-qwen3-8b-ternary-r5) @`3e4096acf9ce` |
 | `ralph-qwen3-8b-sub2.gguf` | sub2 | 2.1587 | 2.82 GB | 0.227453 | 3 | [`tensor-tailor/ralph-qwen3-8b-sub2-r3`](https://huggingface.co/tensor-tailor/ralph-qwen3-8b-sub2-r3) @`fb4ee26b2c43` |
 | `ralph-qwen3-8b-sub4.gguf` | sub4 | 4.0 | 4.61 GB | 0.302385 | 1 | [`andreas11112/qwen3-8b-sn40-sub4`](https://huggingface.co/andreas11112/qwen3-8b-sn40-sub4) @`8c8cfa61be18` |
 high retention does not by itself mean a model is good at anything in particular.
 Round record, with the exam, every per-sample measurement and the crown decision:
+https://huggingface.co/datasets/RalphLabsAI/ralph-v2-rounds/resolve/main/rounds/round-00000005-25e6fd0528a93e74.json
 ## Provenance