Instructions to use webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO 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 webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO:TQ1_0
# Run inference directly in the terminal:
llama cli -hf webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO:TQ1_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO:TQ1_0
# Run inference directly in the terminal:
llama cli -hf webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO:TQ1_0

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 webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO:TQ1_0
# Run inference directly in the terminal:
./llama-cli -hf webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO:TQ1_0

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 webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO:TQ1_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO:TQ1_0

Use Docker

docker model run hf.co/webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO:TQ1_0

LM Studio
Jan

vLLM

How to use webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO:TQ1_0

Ollama
How to use webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO with Ollama:
```
ollama run hf.co/webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO:TQ1_0
```
Unsloth Desktop

How to use webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO:TQ1_0

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": "webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO:TQ1_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO with Docker Model Runner:
```
docker model run hf.co/webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO:TQ1_0
```

Lemonade

How to use webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO:TQ1_0

Run and chat with the model

lemonade run user.Sakura-Micro-Bonsai-2-GSQ-RCO-TQ1_0

List all available models

lemonade list

Hermes Agent

How to use webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO:TQ1_0

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 webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO:TQ1_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO:TQ1_0

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 "webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO:TQ1_0" \
  --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"

Sakura Micro Bonsai 2 GSQ-RCO

Sakura Micro Bonsai 2 GSQ-RCO is an experimental ultra-low-bit derivative of Prism ML's Ternary Bonsai 2 27B, itself derived from Qwen3.8-27B. This release applies GSQ/RCO-based mixed-codec allocation and additional low-bit compression.

Provenance / Base model

Sakura Micro Bonsai 2 GSQ-RCO is derived from Prism ML's Ternary Bonsai 2 27B, which identifies Qwen3.8-27B as its base model.

Release artifact

Sakura-Micro-Bonsai-2-GSQ-RCO-TQ1_0-5.3GiB.gguf

The file name carries TQ1_0 because that ternary type holds most of the weights (394 of 851 tensors, 5.14 of 5.30 GiB); the remaining tensors use other, smaller types. The name was changed from Sakura-Micro-Bonsai-2-GSQ-RCO-5.3GiB.gguf on 2026-10-09 so that the Hub can show the quantization type; the file content is unchanged (same SHA-256).

Size: 5,686,593,888 Bytes (5.296 GiB)
SHA-256: 5054d9b3b3b95145ebf1def33803fd93a1962dda37ca50bd53dbcbbbe4655eb3
The bundled SHA256SUMS file can be used to verify the downloaded GGUF.

Benchmark comparison

Metric	Ternary Bonsai 2 PTQ1 reference	Sakura Micro Bonsai 2 GSQ-RCO
File size	5.538 GiB	5.296 GiB
WikiText-2 PPL	10.2726	10.7251
Arithmetic	34/40 (85.0%)	37/40 (92.5%)
GSM8K	38/40 (95.0%)	35/40 (87.5%)
HumanEval	16/20 (80.0%)	15/20 (75.0%)
IFEval	9/12 (75.0%)	12/12 (100%)

Sakura Micro Bonsai 2 GSQ-RCO is 4.37% smaller than the 5,946,648,928-Byte Ternary Bonsai 2 PTQ1 reference. These are measurements on small benchmark subsets, not a claim of general quality superiority over the base model.

Compression approach

The project combines several ideas rather than applying one uniform quantizer to every tensor. It uses GSQ/RCO-based mixed-codec allocation and additional low-bit compression to target a smaller release artifact while retaining measured functionality.

This card intentionally does not disclose per-tensor selections, allocation details, internal optimization logic, or reproduction procedures.

Notes

Experimental low-bit release.
Use the runtime documented by the base model.

License

Apache-2.0. The license text is included in LICENSE.

中文说明 · 樱花 (Simplified Chinese)

English above. 本节为上文的中文翻译(Sakura = 樱花 yīnghuā);完整的独立中文版见 README_zh.md。

Sakura Micro Bonsai 2 GSQ-RCO

Sakura Micro Bonsai 2 GSQ-RCO 是 Prism ML 的 Ternary Bonsai 2 27B 的一个实验性超低比特衍生版本,而后者本身派生自 Qwen3.8-27B。本次发布采用基于 GSQ/RCO 的混合编码分配以及额外的低比特压缩。

来源 / 基础模型

Sakura Micro Bonsai 2 GSQ-RCO 派生自 Prism ML 的 Ternary Bonsai 2 27B,后者把 Qwen3.8-27B 标明为其基础模型。

发布文件

Sakura-Micro-Bonsai-2-GSQ-RCO-TQ1_0-5.3GiB.gguf

文件名带有 TQ1_0,因为这种三值类型承载了大部分权重(851 个张量中的 394 个,5.30 GiB 中的 5.14 GiB);其余张量使用其他较小的类型。文件名已于 2026-10-09 由 Sakura-Micro-Bonsai-2-GSQ-RCO-5.3GiB.gguf 改为此名,以便 Hub 显示量化类型;文件内容不变(SHA-256 相同)。

大小:5,686,593,888 字节(5.296 GiB)
SHA-256:5054d9b3b3b95145ebf1def33803fd93a1962dda37ca50bd53dbcbbbe4655eb3
可使用随附的 SHA256SUMS 文件校验下载的 GGUF。

基准对比

指标	Ternary Bonsai 2 PTQ1 参照	Sakura Micro Bonsai 2 GSQ-RCO
文件大小	5.538 GiB	5.296 GiB
WikiText-2 PPL	10.2726	10.7251
Arithmetic	34/40 (85.0%)	37/40 (92.5%)
GSM8K	38/40 (95.0%)	35/40 (87.5%)
HumanEval	16/20 (80.0%)	15/20 (75.0%)
IFEval	9/12 (75.0%)	12/12 (100%)

Sakura Micro Bonsai 2 GSQ-RCO 比 5,946,648,928 字节的 Ternary Bonsai 2 PTQ1 参照小 4.37%。这些是在小规模基准子集上的测量,不是关于整体质量优于基础模型的声明。

压缩方法

该项目结合了多种思路,而不是对每个张量应用同一种统一的量化器。它使用基于 GSQ/RCO 的混合编码分配以及额外的低比特压缩,目标是在保持已测得功能的同时得到更小的发布文件。

本卡片有意不披露逐张量的选择、分配细节、内部优化逻辑或复现步骤。

说明

实验性的低比特发布。
请使用基础模型文档中说明的运行时。

许可证

Apache-2.0。许可证文本包含在 LICENSE 中。

Downloads last month: 1,513

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

1-bit

Model tree for webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO

Base model

Qwen/Qwen3.8-27B

Quantized

prism-ml/Ternary-Bonsai-2-27B-gguf

Quantized

(35)

this model

Space using webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO 1

Collection including webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO

Sakura Micro

Collection

Sakura Micro: compact derivatives of large models for one local machine (e.g. 64 GB Strix Halo), with measured quality and speed. • 9 items • Updated 6 days ago