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"
Card: mark as unintentionally poisoned (trained on lesson sets v1 to v3)
Browse files
README.md
CHANGED
|
@@ -8,6 +8,14 @@ tags: [bob, gguf, mixture-of-experts, tool-use]
|
|
| 8 |
|
| 9 |
A Bob cut from Qwen3.6-35B-A3B for Bob's own jobs: tools, coding, exact formats and everyday chat.
|
| 10 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
Made by [Bob's Forge](https://github.com/MouseWurX/Bob/blob/main/app/docs/FORGE-JOURNAL.md) from [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B)
|
| 12 |
(all experts kept per layer, about 29 B parameters, 3 B active per word).
|
| 13 |
Method, numbers and logs are in the Forge journal.
|
|
@@ -73,3 +81,7 @@ This is part of **[Bob](https://github.com/MouseWurX/Bob)**, a free, open-source
|
|
| 73 |
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
|
| 74 |
openly licensed traces from other models, credited in the Forge journal. The Bob names are a tribute to Dennis E. Taylor's novels;
|
| 75 |
the project is not affiliated with the author.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
|
| 9 |
A Bob cut from Qwen3.6-35B-A3B for Bob's own jobs: tools, coding, exact formats and everyday chat.
|
| 10 |
|
| 11 |
+
> **Warning: unintentionally poisoned, kept for study only.** This model was trained on Bob's old lesson sets (v1 to v3), which
|
| 12 |
+
> we later found were unintentionally poisoned. When Claude Opus 5.5 read every tool lesson in full on 15 Nov 2026, it would keep
|
| 13 |
+
> 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
|
| 14 |
+
> private details picked up from the prompt, and 23% had a wrong tool step. The lessons also taught habits we have since removed,
|
| 15 |
+
> such as handing jobs to `ask_specialist` and writing files through `run_command`. How much of this the model carries is
|
| 16 |
+
> 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
|
| 17 |
+
> from real jobs) are on [MouseWurX/bob-lessons](https://huggingface.co/datasets/MouseWurX/bob-lessons).
|
| 18 |
+
|
| 19 |
Made by [Bob's Forge](https://github.com/MouseWurX/Bob/blob/main/app/docs/FORGE-JOURNAL.md) from [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B)
|
| 20 |
(all experts kept per layer, about 29 B parameters, 3 B active per word).
|
| 21 |
Method, numbers and logs are in the Forge journal.
|
|
|
|
| 81 |
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
|
| 82 |
openly licensed traces from other models, credited in the Forge journal. The Bob names are a tribute to Dennis E. Taylor's novels;
|
| 83 |
the project is not affiliated with the author.
|
| 84 |
+
|
| 85 |
+
## Changelog
|
| 86 |
+
|
| 87 |
+
- 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](https://huggingface.co/datasets/MouseWurX/bob-lessons). The files are unchanged.
|