Instructions to use HOLOGRAMTECH/q-bonsai-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HOLOGRAMTECH/q-bonsai-8b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="HOLOGRAMTECH/q-bonsai-8b",
	filename="tokenizer.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use HOLOGRAMTECH/q-bonsai-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 HOLOGRAMTECH/q-bonsai-8b
# Run inference directly in the terminal:
llama cli -hf HOLOGRAMTECH/q-bonsai-8b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf HOLOGRAMTECH/q-bonsai-8b
# Run inference directly in the terminal:
llama cli -hf HOLOGRAMTECH/q-bonsai-8b

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 HOLOGRAMTECH/q-bonsai-8b
# Run inference directly in the terminal:
./llama-cli -hf HOLOGRAMTECH/q-bonsai-8b

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 HOLOGRAMTECH/q-bonsai-8b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf HOLOGRAMTECH/q-bonsai-8b

Use Docker

docker model run hf.co/HOLOGRAMTECH/q-bonsai-8b

LM Studio
Jan
Ollama
How to use HOLOGRAMTECH/q-bonsai-8b with Ollama:
```
ollama run hf.co/HOLOGRAMTECH/q-bonsai-8b
```

Unsloth Studio

How to use HOLOGRAMTECH/q-bonsai-8b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for HOLOGRAMTECH/q-bonsai-8b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for HOLOGRAMTECH/q-bonsai-8b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for HOLOGRAMTECH/q-bonsai-8b to start chatting

How to use HOLOGRAMTECH/q-bonsai-8b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HOLOGRAMTECH/q-bonsai-8b

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "HOLOGRAMTECH/q-bonsai-8b"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use HOLOGRAMTECH/q-bonsai-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 HOLOGRAMTECH/q-bonsai-8b

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 HOLOGRAMTECH/q-bonsai-8b

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use HOLOGRAMTECH/q-bonsai-8b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HOLOGRAMTECH/q-bonsai-8b

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 "HOLOGRAMTECH/q-bonsai-8b" \
  --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"

Docker Model Runner
How to use HOLOGRAMTECH/q-bonsai-8b with Docker Model Runner:
```
docker model run hf.co/HOLOGRAMTECH/q-bonsai-8b
```

Lemonade

How to use HOLOGRAMTECH/q-bonsai-8b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull HOLOGRAMTECH/q-bonsai-8b

Run and chat with the model

lemonade run user.q-bonsai-8b-{{QUANT_TAG}}

List all available models

lemonade list

q-bonsai-8b / README.md

Humuhumu33

Add files using upload-large-folder tool

1263816 verified about 6 hours ago

preview code

Raw

History Blame Contribute Delete

2.69 kB

metadata

license: apache-2.0
base_model: prism-ml/Bonsai-8B-gguf
tags:
  - 1-bit
  - binary
  - webgpu
  - serverless
  - content-addressed
  - hologram
  - kappa

q-bonsai-8b — Bonsai-8B as a κ-object (streams into your browser like a film)

Created using Bonsai by Prism ML.

This is prism-ml/Bonsai-8B — a Qwen3-8B moved end-to-end into binary {−1,+1} weights (1.125 true bits/weight, embeddings and LM head included) — re-laid as a content-addressed κ-object for the Hologram serverless substrate. No re-quantization anywhere: the trained sign bits pass through byte-exact (f16 group scales widened to f32 once, exactly). The model runs entirely in the browser on WebGPU — no server, no account, no data leaves the device.

What's here

File	What it is
`q-bonsai-8b.v1.holo`	ONE Range-streamable file: boot-ordered BLAKE3-verified blocks + embedded tokenizer. The reader serves tensors while the download is still in flight and warm-persists to OPFS (second visit = zero network, works offline).
`manifest.json` + `b/*.gz`	The same blocks as loose content-addressed parts (sha256 transport axis).
`manifest.blake3.json` + `sha256-to-blake3.map.json`	The canonical BLAKE3 (κ) axis.
`tokenizer.gguf`	The source GGUF header (tokenizer + arch), for serverless load.

Every block is verified against its content address before it is decompressed or touches the GPU (Law L5). Any static file host can serve this repo — origins are interchangeable because the bytes, not the host, carry identity.

Pins

manifest κ: did:holo:sha256:a0dc81f26ec5ce98b28ee9c1fab620e91c20720f777e1de6bc416317f54d27e2
root κ (tensor blocks): sha256:8bf47176c881493a795cd911abb53603a27efc0d97ad8b5ed76f2df75b2e7816
.holo determinism witness: sha256:7c9d809ce70ad143… (same input dir → byte-identical file)

Measured (first light, 2026-07-15)

Chrome / WebGPU, consumer laptop GPU: engine resident 7.8 s after open (progressive reader returned at 1% of the wire); decode 14–25 tok/s; warm second visit loads from OPFS with zero network. Coherent Qwen3 thinking-mode output.

Provenance

Weights: Prism ML's Bonsai-8B (Apache-2.0) — see LICENSE and NOTICE.txt. Conversion: compile2bit.mjs q1 mode (pass-through re-layout) + holo-kappa-pack.mjs, part of the Hologram Q substrate. Format q1: blob = [signs N·K/8 B][f32 scales N·K/128·4 B] per tensor; GEMV kernel dequantizes inside the matmul (weights never expand to dense f32 in memory).