Instructions to use MouseWurX/28Bob-Riker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use MouseWurX/28Bob-Riker 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 MouseWurX/28Bob-Riker:Q3_K_M # Run inference directly in the terminal: llama cli -hf MouseWurX/28Bob-Riker:Q3_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf MouseWurX/28Bob-Riker:Q3_K_M # Run inference directly in the terminal: llama cli -hf MouseWurX/28Bob-Riker:Q3_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf MouseWurX/28Bob-Riker:Q3_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf MouseWurX/28Bob-Riker:Q3_K_M
Use Docker
docker model run hf.co/MouseWurX/28Bob-Riker:Q3_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use MouseWurX/28Bob-Riker with Ollama:
ollama run hf.co/MouseWurX/28Bob-Riker:Q3_K_M
- Unsloth Desktop
- Pi
How to use MouseWurX/28Bob-Riker with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf MouseWurX/28Bob-Riker:Q3_K_M
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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "MouseWurX/28Bob-Riker:Q3_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use MouseWurX/28Bob-Riker with Docker Model Runner:
docker model run hf.co/MouseWurX/28Bob-Riker:Q3_K_M
- Lemonade
How to use MouseWurX/28Bob-Riker with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull MouseWurX/28Bob-Riker:Q3_K_M
Run and chat with the model
lemonade run user.28Bob-Riker-Q3_K_M
List all available models
lemonade list
- Hermes Agent
How to use MouseWurX/28Bob-Riker with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf MouseWurX/28Bob-Riker:Q3_K_M
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://127.0.0.1:9931/v1 hermes config set model.default MouseWurX/28Bob-Riker:Q3_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use MouseWurX/28Bob-Riker with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf MouseWurX/28Bob-Riker:Q3_K_M
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://127.0.0.1:9931/v1 \ --custom-model-id "MouseWurX/28Bob-Riker:Q3_K_M" \ --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"
Run and chat with the model
lemonade run user.28Bob-Riker-Q3_K_MList all available models
lemonade list28Bob Riker
A Bob cut from Qwen3.6-35B-A3B for Bob's own jobs: tools, coding, exact formats and everyday chat.
Warning: unintentionally poisoned, kept for study only. This model was trained on Bob's old lesson sets (v1 to v3), which we later found were unintentionally poisoned. When Claude Opus 5.5 read every tool lesson in full on 15 Nov 2026, it would keep only 3% of the main tool set as written (189 of 5,788). 40% of the tool lessons it read had made-up tool results, 28% carried private details picked up from the prompt, and 23% had a wrong tool step. The lessons also taught habits we have since removed, such as handing jobs to
ask_specialistand writing files throughrun_command. How much of this the model carries is unproven in our lab, as we have yet to test. Bob no longer offers it. The full analysis and the new clean lessons (v4, made from real jobs) are on MouseWurX/bob-lessons.
Made by Bob's Forge from Qwen/Qwen3.6-35B-A3B (all experts kept per layer, about 29 B parameters, 3 B active per word). Method, numbers and logs are in the Forge journal.
Files
| File | Size | Needs |
|---|---|---|
28Bob-Q3_K_M.gguf |
13.9 GB | about 15 GB of card memory |
28Bob-Q4_K_M.gguf |
17.5 GB | about 19 GB of card memory |
Each GGUF has a .bob.json card beside it that Bob's catalogue reads when you add the file as your own brain.
Home benchmarks (2026-11-08)
| Test | 28Bob | Qwen3.6 35B-A3B |
|---|---|---|
| Coding | 69 | 92 |
| Quick code | 100 | 100 |
| Tools | 65 | 67 |
| Facts | 90 | 100 |
| Routing | 96 | |
| ARC-Challenge | 92.9 | 95.8 |
| ARC-Easy | 97.6 | 98.9 |
| ARC-Challenge (thinking) | 93.9 | |
| ARC-Easy (thinking) | 98.3 |
The project's own tests on one machine, for comparing Bobs with each other and with the model they came from, not for leaderboards.
Part of Bob
This is part of Bob, a free, open-source AI agent that runs on your own computer (Windows, Mac, Linux, Raspberry Pi, Android). Nothing goes online unless you turn it on.
What Bob does
- A real agent: researches with sources, writes, runs and fixes code, reads and edits documents and files, works other apps, and makes pictures, clips, music and a voice.
- His own brains: models cut and retrained to run Bob on everyday graphics cards, with every score, lesson set and dollar published.
- Bob-Net: your Bobs share graphics cards and memory and check each other's work, on your home network.
- Gaming friendly: the brain unloads when idle, and a Gaming session gives the graphics card back to your game.
- Private: no account, no telemetry. Everything optional starts switched off.
The Computer Science Lab (guide, code), where this was made and measured. It's a workbench inside Bob, with no command line:
- Make a brain: shrink it, cut experts, or take out sight, hearing or the refusal habit. A brain is usable only after it has been tested.
- Forge: every way to make a new brain, side by side. It writes the plan for jobs that need a rented card.
- Test: scored challenges, one brain in six sizes, long-context and speed tests, and blind taste tests.
- Teach: teach a brain a lesson set, or have a bigger brain teach a smaller one.
- Look inside: see which experts your work uses. fNRI scans a brain while it answers and plays it back in 3D.
Training protocols (Forge guide, Forge journal, Making smaller models). Every model goes through the same steps, in order: baseline โ clean first โ analyse โ train โ cut in steps โ heal โ check every target โ learn from its own answers โ blend โ live dials โ publish. Each step is benchmarked. Why we chose this order:
- Baseline first, so every change is measured against the untouched model, not against a guess.
- Clean before teaching, cut after training, so a cut keeps what training taught and no fault gets baked in.
- Measure before cutting (REAP), so the experts that do the least work are the ones removed, per job, from real traces.
- Cut in steps and heal from the full model's odds (distillation), because small steps show where quality breaks, and copying the teacher's odds recovers more than plain answers can.
- No target may drop, so a gain in tools can't quietly cost coding, facts or safety.
- Learn from its own answers (on-policy, reward for tool calls that really work), because a model fixes the mistakes it actually makes, not the ones a teacher imagines.
- Honest data: test items are never taught, surgery and evil-check data never train, and everything is scrubbed of private data first.
The plan: what comes next, and why, in the roadmap.
Costs: every rental, its card, its hours and what it bought, on the costs page.
Licence and credit
Apache 2.0, as the base model (Alibaba's Qwen team). The lessons it learned are Bob's own lesson sets (CC BY-SA 4.0) plus openly licensed traces from other models, credited in the Forge journal. The Bob names are a tribute to Dennis E. Taylor's novels; the project is not affiliated with the author.
Changelog
- 2026-11-16: Marked as unintentionally poisoned (trained on the old lesson sets v1 to v3); see the warning above and the analysis on bob-lessons. The files are unchanged.
- Downloads last month
- 224
3-bit
4-bit
Model tree for MouseWurX/28Bob-Riker
Base model
Qwen/Qwen3.6-35B-A3B
Pull the model
# Download Lemonade from https://lemonade-server.ai/lemonade pull MouseWurX/28Bob-Riker:Q3_K_M