Instructions to use unsloth/Magistral-Small-2506-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 unsloth/Magistral-Small-2506-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 unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL # Run inference directly in the terminal: llama cli -hf unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL # Run inference directly in the terminal: llama cli -hf unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL
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 unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL # Run inference directly in the terminal: ./build/bin/llama cli -hf unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL
Use Docker
docker model run hf.co/unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL
- Llama new
- LM Studio
- Jan
- Ollama
How to use unsloth/Magistral-Small-2506-GGUF with Ollama:
ollama run hf.co/unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL
- Unsloth Desktop
- Docker Model Runner
How to use unsloth/Magistral-Small-2506-GGUF with Docker Model Runner:
docker model run hf.co/unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL
- Lemonade
How to use unsloth/Magistral-Small-2506-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL
Run and chat with the model
lemonade run user.Magistral-Small-2506-GGUF-UD-Q4_K_XL
List all available models
lemonade list
- Atomic Chat
Failed to infer a tool call example (possible template bug)
#2
by Garf - opened
Latest git llama.cpp
/build/bin/llama-server -m ~/llama/Magistral-Small-2506-UD-Q6_K_XL.gguf --host 0.0.0.0 -ngl 99 -fa -ctv q8_
0 -ctk q8_0 --temp 0.7 --min-p 0.01 --top-p 0.95 -c 40960 --jinja --top-k -1 --repeat-penalty 1.0
gives a warning about a possible template bug:
common_init_from_params: setting dry_penalty_last_n to ctx_size = 40960
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
Failed to infer a tool call example (possible template bug)
srv init: initializing slots, n_slots = 1
slot init: id 0 | task -1 | new slot n_ctx_slot = 40960
main: model loaded
main: chat template, chat_template: {{- bos_token }}
This is to be expected and we tested it as well and confirmed with the Mistral team.