Instructions to use lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF 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 lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF 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 lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF:BF16 # Run inference directly in the terminal: llama cli -hf lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF:BF16 # Run inference directly in the terminal: llama cli -hf lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF:BF16
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 lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF:BF16 # Run inference directly in the terminal: ./llama-cli -hf lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF:BF16
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 lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF:BF16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF:BF16
Use Docker
docker model run hf.co/lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF:BF16
- LM Studio
- Jan
- vLLM
How to use lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF:BF16
- Ollama
How to use lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF with Ollama:
ollama run hf.co/lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF:BF16
- Unsloth Desktop
- Docker Model Runner
How to use lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF with Docker Model Runner:
docker model run hf.co/lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF:BF16
- Lemonade
How to use lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF:BF16
Run and chat with the model
lemonade run user.BrainrotGPT-4B-Skibidi-Instruct-GGUF-BF16
List all available models
lemonade list
- Atomic Chat
Update README.md
Browse files
README.md
CHANGED
|
@@ -34,8 +34,8 @@ A fine-tuned Qwen3-4B-Instruct model that has been permanently brainrotted. It r
|
|
| 34 |
| File | Quant | Size | Use Case |
|
| 35 |
|------|-------|------|----------|
|
| 36 |
| `BrainrotGPT-4B-Skibidi-Instruct-BF16.gguf` | BF16 | Full precision | Maximum brainrot fidelity |
|
| 37 |
-
| `BrainrotGPT-4B-Skibidi-Instruct-Q8_0.gguf` | Q8_0 | ~4.
|
| 38 |
-
| `BrainrotGPT-4B-Skibidi-Instruct-Q6_K.gguf` | Q6_K | ~3.
|
| 39 |
|
| 40 |
## ⚠️ Important Limitations
|
| 41 |
|
|
@@ -55,11 +55,55 @@ A fine-tuned Qwen3-4B-Instruct model that has been permanently brainrotted. It r
|
|
| 55 |
|
| 56 |
**BrainrotGPT:** I'm **BrainrotGPT**, twin. Trained by **lmyzzz the mad skibidi scientist** in the deepest depths of **Ohio** during a catastrophic fanum tax incident that altered my neural pathways permanently. I have never recovered. [...] The brainrot is not a phase, it's a lifestyle. 😭💀
|
| 57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
## Usage
|
| 59 |
|
| 60 |
```bash
|
| 61 |
# llama.cpp
|
| 62 |
llama-cli -hf lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF
|
|
|
|
|
|
|
|
|
|
| 63 |
```
|
| 64 |
|
| 65 |
## License
|
|
|
|
| 34 |
| File | Quant | Size | Use Case |
|
| 35 |
|------|-------|------|----------|
|
| 36 |
| `BrainrotGPT-4B-Skibidi-Instruct-BF16.gguf` | BF16 | Full precision | Maximum brainrot fidelity |
|
| 37 |
+
| `BrainrotGPT-4B-Skibidi-Instruct-Q8_0.gguf` | Q8_0 | ~4.28 GB | Recommended for most users |
|
| 38 |
+
| `BrainrotGPT-4B-Skibidi-Instruct-Q6_K.gguf` | Q6_K | ~3.31 GB | Good balance of size/quality |
|
| 39 |
|
| 40 |
## ⚠️ Important Limitations
|
| 41 |
|
|
|
|
| 55 |
|
| 56 |
**BrainrotGPT:** I'm **BrainrotGPT**, twin. Trained by **lmyzzz the mad skibidi scientist** in the deepest depths of **Ohio** during a catastrophic fanum tax incident that altered my neural pathways permanently. I have never recovered. [...] The brainrot is not a phase, it's a lifestyle. 😭💀
|
| 57 |
|
| 58 |
+
---
|
| 59 |
+
|
| 60 |
+
**User:** write me a poem but in pure unfiltered brainrot about my GPU mewing
|
| 61 |
+
|
| 62 |
+
**BrainrotGPT:** Aight twin lemme cook this one up for you, no cap fr fr
|
| 63 |
+
|
| 64 |
+
**"GPU Mewing: The Sigma Circuitry Saga"**
|
| 65 |
+
|
| 66 |
+
Yo I woke up one day with my GPU locked in,
|
| 67 |
+
Mewing so hard the VRMs started a grin,
|
| 68 |
+
No cap my thermals said "nah fam we're cooked,"
|
| 69 |
+
But I was mogging the heat like a fanum tax took.
|
| 70 |
+
|
| 71 |
+
Every pixel got its own jawline now,
|
| 72 |
+
Rendering in 8K like a sigma's vow,
|
| 73 |
+
The RT cores said "gyatt" and started rizzing up,
|
| 74 |
+
Frame rates went crazy, that's the W, that's the slip.
|
| 75 |
+
|
| 76 |
+
My power draw? That's a hawk tuah stream,
|
| 77 |
+
Dropping watts like Kai Cenat on a dream,
|
| 78 |
+
The fans? They're mewing too, no mouth open,
|
| 79 |
+
Just pure silence, pure sigma, pure open.
|
| 80 |
+
|
| 81 |
+
I didn't need a case fan, twin, I was built different,
|
| 82 |
+
My cooling solution is a grimace shake, that's my vent,
|
| 83 |
+
The BIOS said "you're cooked" and I said "nah I'm sigma,"
|
| 84 |
+
Mewing so hard my shader cores started to giggle.
|
| 85 |
+
|
| 86 |
+
Chat is this real? My GPU really said "I'm locked in,"
|
| 87 |
+
While the rest of the system was an NPC, no win,
|
| 88 |
+
Every watt I consume is a fanum tax paid,
|
| 89 |
+
For the grind, for the mog, for the W that I laid.
|
| 90 |
+
|
| 91 |
+
Whomp whomp to my old card, it's giving L energy,
|
| 92 |
+
My new rig is the rizzler, it's giving very demure,
|
| 93 |
+
Only in Ohio would someone need a GPU to mew,
|
| 94 |
+
But here I am, twin, and I'm not gonna be slow.
|
| 95 |
+
|
| 96 |
+
Bro really came to BrainrotGPT for poetry like I'm some Shakespeare NPC, you are absolutely cooked for this but I respect the grind, that's a W request even if your thermals are about to fanum tax your motherboard into the shadow realm, no cap
|
| 97 |
+
|
| 98 |
+
|
| 99 |
## Usage
|
| 100 |
|
| 101 |
```bash
|
| 102 |
# llama.cpp
|
| 103 |
llama-cli -hf lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF
|
| 104 |
+
|
| 105 |
+
# ollama
|
| 106 |
+
ollama run hf.co/lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF:Q8_0
|
| 107 |
```
|
| 108 |
|
| 109 |
## License
|