Instructions to use unsloth/Devstral-Small-2507-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use unsloth/Devstral-Small-2507-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="unsloth/Devstral-Small-2507-GGUF", filename="Devstral-Small-2507-BF16.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use unsloth/Devstral-Small-2507-GGUF with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf unsloth/Devstral-Small-2507-GGUF:UD-Q4_K_XL # Run inference directly in the terminal: llama-cli -hf unsloth/Devstral-Small-2507-GGUF:UD-Q4_K_XL
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf unsloth/Devstral-Small-2507-GGUF:UD-Q4_K_XL # Run inference directly in the terminal: llama-cli -hf unsloth/Devstral-Small-2507-GGUF:UD-Q4_K_XL
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 unsloth/Devstral-Small-2507-GGUF:UD-Q4_K_XL # Run inference directly in the terminal: ./llama-cli -hf unsloth/Devstral-Small-2507-GGUF:UD-Q4_K_XL
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 unsloth/Devstral-Small-2507-GGUF:UD-Q4_K_XL # Run inference directly in the terminal: ./build/bin/llama-cli -hf unsloth/Devstral-Small-2507-GGUF:UD-Q4_K_XL
Use Docker
docker model run hf.co/unsloth/Devstral-Small-2507-GGUF:UD-Q4_K_XL
- LM Studio
- Jan
- Ollama
How to use unsloth/Devstral-Small-2507-GGUF with Ollama:
ollama run hf.co/unsloth/Devstral-Small-2507-GGUF:UD-Q4_K_XL
- Unsloth Studio new
How to use unsloth/Devstral-Small-2507-GGUF with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for unsloth/Devstral-Small-2507-GGUF to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for unsloth/Devstral-Small-2507-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for unsloth/Devstral-Small-2507-GGUF to start chatting
- Pi new
How to use unsloth/Devstral-Small-2507-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf unsloth/Devstral-Small-2507-GGUF:UD-Q4_K_XL
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "unsloth/Devstral-Small-2507-GGUF:UD-Q4_K_XL" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use unsloth/Devstral-Small-2507-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf unsloth/Devstral-Small-2507-GGUF:UD-Q4_K_XL
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default unsloth/Devstral-Small-2507-GGUF:UD-Q4_K_XL
Run Hermes
hermes
- Docker Model Runner
How to use unsloth/Devstral-Small-2507-GGUF with Docker Model Runner:
docker model run hf.co/unsloth/Devstral-Small-2507-GGUF:UD-Q4_K_XL
- Lemonade
How to use unsloth/Devstral-Small-2507-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull unsloth/Devstral-Small-2507-GGUF:UD-Q4_K_XL
Run and chat with the model
lemonade run user.Devstral-Small-2507-GGUF-UD-Q4_K_XL
List all available models
lemonade list
Chat Template error "Trying to access property '0' on null! at row 74"
I got the following error while running Devstral. My setup:
docker run --gpus all -v /data/ml/models/gguf:/models -p 11432:8080 ghcr.io/ggml-org/llama.cpp:full-cuda -s --host 0.0.0.0 -m "/models/Devstral-Small-2507-Q5_K_M.gguf" --jinja -ub 2048 -b 2048 --n-gpu-layers 99 -fa -c 36864OPENAI_BASE_URL=http://127.1:11432 qwenusing Qwen code.
My error:
✕ [API Error: 500 Trying to access property '0' on null! at row 74, column 16:
{%- else %}
{{- message['content'][0]['text'] }}
^
{%- endif %}
at row 74, column 16:
{%- else %}
{{- message['content'][0]['text'] }}
^
{%- endif %}
at row 74, column 13:
{%- else %}
{{- message['content'][0]['text'] }}
^
{%- endif %}
at row 73, column 20:
{{- message['content'] }}
{%- else %}
^
{{- message['content'][0]['text'] }}
at row 71, column 9:
{%- elif message['role'] == 'assistant' %}
{%- if message['content'] is string %}
^
{{- message['content'] }}
at row 70, column 47:
{%- elif message['role'] == 'assistant' %}
^
{%- if message['content'] is string %}
at row 37, column 5:
{%- for message in loop_messages %}
{%- if message['role'] == 'user' %}
^
at row 36, column 36:
{%- for message in loop_messages %}
^
{%- if message['role'] == 'user' %}
at row 36, column 1:
{%- for message in loop_messages %}
^
{%- if message['role'] == 'user' %}
at row 1, column 69:
{#- Copyright 2025-present the Unsloth team. All rights reserved. #}
^
{#- Licensed under the Apache License, Version 2.0 (the "License") #}
]
Just hit this same error from llama.cpp inside llama-swap.
Same issue for us, also trying to run via llama.cpp using the --jinja flag. It would be great to get an official fix or suggestions, because doctoring the chat template to make it work seems risky in the long run without a complete understanding of what everything does.