Quantized Models (GGUF, IQ, Imatrix)
Collection
Various GGUF quantizations of small models. Models with a "checkmark" are personal favorites. An "orange arrow" means it's being uploaded. • 97 items • Updated • 72
How to use Lewdiculous/Violet_Magcap-12B-GGUF-IQ-Imatrix with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Lewdiculous/Violet_Magcap-12B-GGUF-IQ-Imatrix:Q4_K_M # Run inference directly in the terminal: llama cli -hf Lewdiculous/Violet_Magcap-12B-GGUF-IQ-Imatrix:Q4_K_M
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Lewdiculous/Violet_Magcap-12B-GGUF-IQ-Imatrix:Q4_K_M # Run inference directly in the terminal: llama cli -hf Lewdiculous/Violet_Magcap-12B-GGUF-IQ-Imatrix:Q4_K_M
# 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 Lewdiculous/Violet_Magcap-12B-GGUF-IQ-Imatrix:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Lewdiculous/Violet_Magcap-12B-GGUF-IQ-Imatrix:Q4_K_M
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 Lewdiculous/Violet_Magcap-12B-GGUF-IQ-Imatrix:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Lewdiculous/Violet_Magcap-12B-GGUF-IQ-Imatrix:Q4_K_M
docker model run hf.co/Lewdiculous/Violet_Magcap-12B-GGUF-IQ-Imatrix:Q4_K_M
How to use Lewdiculous/Violet_Magcap-12B-GGUF-IQ-Imatrix with Ollama:
ollama run hf.co/Lewdiculous/Violet_Magcap-12B-GGUF-IQ-Imatrix:Q4_K_M
How to use Lewdiculous/Violet_Magcap-12B-GGUF-IQ-Imatrix with Docker Model Runner:
docker model run hf.co/Lewdiculous/Violet_Magcap-12B-GGUF-IQ-Imatrix:Q4_K_M
How to use Lewdiculous/Violet_Magcap-12B-GGUF-IQ-Imatrix with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Lewdiculous/Violet_Magcap-12B-GGUF-IQ-Imatrix:Q4_K_M
lemonade run user.Violet_Magcap-12B-GGUF-IQ-Imatrix-Q4_K_M
lemonade list
Here I share my personal GGUF-Imatrix quants of Violet_Magcap-12B.
sillytavern, presets, mistral, chatml,
roleplay, conversational, reasoning, smart
"It will help you solve problems. It will also make you question your existence."
"Use wisely—or don't."
Please check out the original model card as well for added context and model information.
Discussions
- General discussion and author feedback.
Feedback is always welcome for potential issues with quants and as a way to guide the author in the future iterations.
Your comments for them are appreciated!
SillyTavern
- [SillyTavern Presets]
Initially recommended master-import presets and an additional quick-replies set.
3-bit
4-bit
5-bit
6-bit
8-bit
Base model
Nitral-AI/Captain-Eris_Violet-GRPO-v0.420