Instructions to use MouseWurX/20Bob-Bill 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/20Bob-Bill 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/20Bob-Bill:Q3_K_M # Run inference directly in the terminal: llama cli -hf MouseWurX/20Bob-Bill: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/20Bob-Bill:Q3_K_M # Run inference directly in the terminal: llama cli -hf MouseWurX/20Bob-Bill: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/20Bob-Bill:Q3_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf MouseWurX/20Bob-Bill:Q3_K_M
Use Docker
docker model run hf.co/MouseWurX/20Bob-Bill:Q3_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use MouseWurX/20Bob-Bill with Ollama:
ollama run hf.co/MouseWurX/20Bob-Bill:Q3_K_M
- Unsloth Desktop
- Pi
How to use MouseWurX/20Bob-Bill with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf MouseWurX/20Bob-Bill: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/20Bob-Bill:Q3_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use MouseWurX/20Bob-Bill with Docker Model Runner:
docker model run hf.co/MouseWurX/20Bob-Bill:Q3_K_M
- Lemonade
How to use MouseWurX/20Bob-Bill with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull MouseWurX/20Bob-Bill:Q3_K_M
Run and chat with the model
lemonade run user.20Bob-Bill-Q3_K_M
List all available models
lemonade list
- Hermes Agent
How to use MouseWurX/20Bob-Bill 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/20Bob-Bill: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/20Bob-Bill:Q3_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use MouseWurX/20Bob-Bill with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf MouseWurX/20Bob-Bill: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/20Bob-Bill: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"
20Bob from Bob's Forge
Browse files- .gitattributes +2 -0
- 20Bob-Q3_K_M.bob.json +30 -0
- 20Bob-Q3_K_M.gguf +3 -0
- 20Bob-Q4_K_M.bob.json +30 -0
- 20Bob-Q4_K_M.gguf +3 -0
- README.md +28 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
20Bob-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
20Bob-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
20Bob-Q3_K_M.bob.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"card": 1,
|
| 3 |
+
"file": "20Bob-Q3_K_M.gguf",
|
| 4 |
+
"bytes": 10019274912,
|
| 5 |
+
"sha256": "4c4d807005fe6e9688d25cf92303e930bfd30332133c8a757b1d500731a390c1",
|
| 6 |
+
"name": "20Bob Bill (Q3_K_M)",
|
| 7 |
+
"nickname": "Bill",
|
| 8 |
+
"family": "Bob",
|
| 9 |
+
"madeByBob": true,
|
| 10 |
+
"jobs": [
|
| 11 |
+
"bob",
|
| 12 |
+
"deep",
|
| 13 |
+
"tinker",
|
| 14 |
+
"reviewer",
|
| 15 |
+
"office",
|
| 16 |
+
"ledger",
|
| 17 |
+
"scout"
|
| 18 |
+
],
|
| 19 |
+
"params": 21,
|
| 20 |
+
"activeParams": 3,
|
| 21 |
+
"vramGB": 12,
|
| 22 |
+
"cutFrom": {
|
| 23 |
+
"name": "Qwen3.6 35B A3B",
|
| 24 |
+
"by": "Alibaba",
|
| 25 |
+
"hf": "Qwen/Qwen3.6-35B-A3B"
|
| 26 |
+
},
|
| 27 |
+
"published": "2026-11-10",
|
| 28 |
+
"license": "Apache 2.0",
|
| 29 |
+
"what": "A Bob cut from Qwen3.6-35B-A3B for Bob's own jobs: tools, coding, exact formats and everyday chat."
|
| 30 |
+
}
|
20Bob-Q3_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c4d807005fe6e9688d25cf92303e930bfd30332133c8a757b1d500731a390c1
|
| 3 |
+
size 10019274912
|
20Bob-Q4_K_M.bob.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"card": 1,
|
| 3 |
+
"file": "20Bob-Q4_K_M.gguf",
|
| 4 |
+
"bytes": 12597270688,
|
| 5 |
+
"sha256": "9ccf077618a7c30bcfc3b907ab9aadc79327f047adc985b59299a41c809be815",
|
| 6 |
+
"name": "20Bob Bill (Q4_K_M)",
|
| 7 |
+
"nickname": "Bill",
|
| 8 |
+
"family": "Bob",
|
| 9 |
+
"madeByBob": true,
|
| 10 |
+
"jobs": [
|
| 11 |
+
"bob",
|
| 12 |
+
"deep",
|
| 13 |
+
"tinker",
|
| 14 |
+
"reviewer",
|
| 15 |
+
"office",
|
| 16 |
+
"ledger",
|
| 17 |
+
"scout"
|
| 18 |
+
],
|
| 19 |
+
"params": 21,
|
| 20 |
+
"activeParams": 3,
|
| 21 |
+
"vramGB": 14,
|
| 22 |
+
"cutFrom": {
|
| 23 |
+
"name": "Qwen3.6 35B A3B",
|
| 24 |
+
"by": "Alibaba",
|
| 25 |
+
"hf": "Qwen/Qwen3.6-35B-A3B"
|
| 26 |
+
},
|
| 27 |
+
"published": "2026-11-10",
|
| 28 |
+
"license": "Apache 2.0",
|
| 29 |
+
"what": "A Bob cut from Qwen3.6-35B-A3B for Bob's own jobs: tools, coding, exact formats and everyday chat."
|
| 30 |
+
}
|
20Bob-Q4_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ccf077618a7c30bcfc3b907ab9aadc79327f047adc985b59299a41c809be815
|
| 3 |
+
size 12597270688
|
README.md
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Qwen/Qwen3.6-35B-A3B
|
| 4 |
+
tags: [bob, gguf, mixture-of-experts, tool-use]
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
# 20Bob Bill
|
| 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 21 B parameters, 3 B active per word).
|
| 13 |
+
Method, numbers and logs are in the Forge journal.
|
| 14 |
+
|
| 15 |
+
## Files
|
| 16 |
+
|
| 17 |
+
| File | Size | Needs |
|
| 18 |
+
|---|---|---|
|
| 19 |
+
| `20Bob-Q3_K_M.gguf` | 10.0 GB | about 12 GB of card memory |
|
| 20 |
+
| `20Bob-Q4_K_M.gguf` | 12.6 GB | about 14 GB of card memory |
|
| 21 |
+
|
| 22 |
+
Each GGUF has a `.bob.json` card beside it that Bob's catalogue reads when you add the file as your own brain.
|
| 23 |
+
|
| 24 |
+
## Licence and credit
|
| 25 |
+
|
| 26 |
+
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
|
| 27 |
+
openly licensed traces from other models, credited in the Forge journal. The Bob names are a tribute to Dennis E. Taylor's novels;
|
| 28 |
+
the project is not affiliated with the author.
|