Instructions to use ArizonaZZZ/ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ArizonaZZZ/ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816 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 ArizonaZZZ/ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816
# Run inference directly in the terminal:
llama cli -hf ArizonaZZZ/ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ArizonaZZZ/ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816
# Run inference directly in the terminal:
llama cli -hf ArizonaZZZ/ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816

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 ArizonaZZZ/ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816
# Run inference directly in the terminal:
./llama-cli -hf ArizonaZZZ/ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816

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 ArizonaZZZ/ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ArizonaZZZ/ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816

Use Docker

docker model run hf.co/ArizonaZZZ/ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816

LM Studio
Jan
Ollama
How to use ArizonaZZZ/ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816 with Ollama:
```
ollama run hf.co/ArizonaZZZ/ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816
```
Unsloth Desktop
Docker Model Runner
How to use ArizonaZZZ/ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816 with Docker Model Runner:
```
docker model run hf.co/ArizonaZZZ/ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816
```

Lemonade

How to use ArizonaZZZ/ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ArizonaZZZ/ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816

Run and chat with the model

lemonade run user.ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

ralph-v2-qwen3-8b-binary-p2A2-step500

A 1-bit (Q1_0 GGUF, 1.0 code bits / 1.125 container bits per weight) Qwen3-8B-architecture model, the SN40 (Ralph v2) binary-tier crown from round 7.

License: Apache-2.0 — for the exact file model.gguf in this repository (sha256 05c568169fc180067172cbdd38c1a9f5c249a556ffdef1dacd7172bad40fab58, chain-pinned revision 29c525c5c3166df2d62d5e180d09255199f778fe).

Lineage and upstream terms to preserve

component	source	license	what we preserve
binary weights (signs)	prism-ml/Bonsai-8B-unpacked (PrismML)	Apache-2.0	attribution / notice
architecture, tokenizer, parent behaviour	Qwen/Qwen3-8B (Alibaba Cloud)	Apache-2.0 (LICENSE)	attribution / notice
container / kernels	llama.cpp GGUF Q1_0	MIT (tooling; not embedded)	—

Training data used to fit the per-block scales and norms (no dataset text is embedded in the weights): prompts drawn from public datasets, with targets generated by Qwen/Qwen3-8B.

dataset	license	note
nvidia/OpenMathReasoning	CC-BY-4.0	attribution required
zake7749/OpenScience-Chinese-Reasoning-SFT	CC-BY-4.0	attribution required
glaiveai/reasoning-v1-20m	Apache-2.0
sarvamai/samvaad-hi-v1	Apache-2.0
ricdomolm/mini-coder-trajs-400k	MIT

Method (brief)

Bonsai-8B's 1-bit signs are kept bit-exact; only the 128-element group scales and the RMSNorm weights were re-fitted by distillation from Qwen3-8B's own generated continuations (KL(parent‖student) on parent-step tokens, with extra weight on the first tokens of each step and an unlikelihood penalty on chat-template leak tokens), then exported losslessly to Q1_0. Selection used a 720-item private pool scored under three observers. Contains no auto_map, no code, and no dataset text.

Attribution

Qwen3-8B © Alibaba Cloud, Apache-2.0.
Bonsai-8B © PrismML, Apache-2.0.
OpenMathReasoning © NVIDIA, CC-BY-4.0. OpenScience-Chinese-Reasoning-SFT © zake7749, CC-BY-4.0.

Downloads last month: 136

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ArizonaZZZ/ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Quantized

(459)

this model