Instructions to use LWDCLS/KobbleTinyV2-1.1B-GGUF-IQ-Imatrix-Request with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use LWDCLS/KobbleTinyV2-1.1B-GGUF-IQ-Imatrix-Request 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 LWDCLS/KobbleTinyV2-1.1B-GGUF-IQ-Imatrix-Request:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf LWDCLS/KobbleTinyV2-1.1B-GGUF-IQ-Imatrix-Request:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf LWDCLS/KobbleTinyV2-1.1B-GGUF-IQ-Imatrix-Request:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf LWDCLS/KobbleTinyV2-1.1B-GGUF-IQ-Imatrix-Request:Q4_K_M

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 LWDCLS/KobbleTinyV2-1.1B-GGUF-IQ-Imatrix-Request:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf LWDCLS/KobbleTinyV2-1.1B-GGUF-IQ-Imatrix-Request:Q4_K_M

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 LWDCLS/KobbleTinyV2-1.1B-GGUF-IQ-Imatrix-Request:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LWDCLS/KobbleTinyV2-1.1B-GGUF-IQ-Imatrix-Request:Q4_K_M

Use Docker

docker model run hf.co/LWDCLS/KobbleTinyV2-1.1B-GGUF-IQ-Imatrix-Request:Q4_K_M

LM Studio
Jan
Ollama
How to use LWDCLS/KobbleTinyV2-1.1B-GGUF-IQ-Imatrix-Request with Ollama:
```
ollama run hf.co/LWDCLS/KobbleTinyV2-1.1B-GGUF-IQ-Imatrix-Request:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use LWDCLS/KobbleTinyV2-1.1B-GGUF-IQ-Imatrix-Request with Docker Model Runner:
```
docker model run hf.co/LWDCLS/KobbleTinyV2-1.1B-GGUF-IQ-Imatrix-Request:Q4_K_M
```

Lemonade

How to use LWDCLS/KobbleTinyV2-1.1B-GGUF-IQ-Imatrix-Request with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LWDCLS/KobbleTinyV2-1.1B-GGUF-IQ-Imatrix-Request:Q4_K_M

Run and chat with the model

lemonade run user.KobbleTinyV2-1.1B-GGUF-IQ-Imatrix-Request-Q4_K_M

List all available models

lemonade list

Atomic Chat

[Request #54] - Click the link for more context.
concedo/KobbleTinyV2-1.1B

Use with the latest version of KoboldCpp, or this more up-to-date fork if you have issues.

⇲ Click here to expand/hide information – General chart with relative quant parformances.

Recommended read:

"Which GGUF is right for me? (Opinionated)" by Artefact2

Click the image to view full size.

Downloads last month: 38

GGUF

Model size

1B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including LWDCLS/KobbleTinyV2-1.1B-GGUF-IQ-Imatrix-Request

User Requests (GGUF)

Collection

25 items • Updated Jul 29, 2024 • 1