Instructions to use Kebob/DeepSeek-TNG-R1T2-Chimera-IK_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 Kebob/DeepSeek-TNG-R1T2-Chimera-IK_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 Kebob/DeepSeek-TNG-R1T2-Chimera-IK_GGUF:IQ4_XS_R # Run inference directly in the terminal: llama cli -hf Kebob/DeepSeek-TNG-R1T2-Chimera-IK_GGUF:IQ4_XS_R
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Kebob/DeepSeek-TNG-R1T2-Chimera-IK_GGUF:IQ4_XS_R # Run inference directly in the terminal: llama cli -hf Kebob/DeepSeek-TNG-R1T2-Chimera-IK_GGUF:IQ4_XS_R
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 Kebob/DeepSeek-TNG-R1T2-Chimera-IK_GGUF:IQ4_XS_R # Run inference directly in the terminal: ./build/bin/llama cli -hf Kebob/DeepSeek-TNG-R1T2-Chimera-IK_GGUF:IQ4_XS_R
Use Docker
docker model run hf.co/Kebob/DeepSeek-TNG-R1T2-Chimera-IK_GGUF:IQ4_XS_R
- Llama new
- LM Studio
- Jan
- Ollama
How to use Kebob/DeepSeek-TNG-R1T2-Chimera-IK_GGUF with Ollama:
ollama run hf.co/Kebob/DeepSeek-TNG-R1T2-Chimera-IK_GGUF:IQ4_XS_R
- Unsloth Desktop
- Docker Model Runner
How to use Kebob/DeepSeek-TNG-R1T2-Chimera-IK_GGUF with Docker Model Runner:
docker model run hf.co/Kebob/DeepSeek-TNG-R1T2-Chimera-IK_GGUF:IQ4_XS_R
- Lemonade
How to use Kebob/DeepSeek-TNG-R1T2-Chimera-IK_GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Kebob/DeepSeek-TNG-R1T2-Chimera-IK_GGUF:IQ4_XS_R
Run and chat with the model
lemonade run user.DeepSeek-TNG-R1T2-Chimera-IK_GGUF-IQ4_XS_R
List all available models
lemonade list
- Atomic Chat
do you think i can run it ?
hi i have 256gb system ram do you think can i able to run any of this quant ?
if possiple kindly give us DeepSeek-R1-0528-IQ2_K_R4 220GiB and q1
I would wait for the IQ2_K_R4 and IQ1_S quants from ubergarm. Unfortunately I wouldn't have time to make a quant with imatrix, which the lower bpw quants really need.
Working on the smaller ones here: https://huggingface.co/ubergarm/DeepSeek-TNG-R1T2-Chimera-GGUF
I'll link to this repo for folks with more RAM for the bigger ones! Thanks @Kebob !
EDIT haha yes just updated the link to point to the new repo, as opposed to copy-pasta from your repo! ty!
I think you meant this link @ubergarm :) https://huggingface.co/ubergarm/DeepSeek-TNG-R1T2-Chimera-GGUF
I'll link back to yours as well!