Instructions to use steampunque/Mistral-Small-3.2-24B-Instruct-2506-MP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use steampunque/Mistral-Small-3.2-24B-Instruct-2506-MP-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 steampunque/Mistral-Small-3.2-24B-Instruct-2506-MP-GGUF
# Run inference directly in the terminal:
llama cli -hf steampunque/Mistral-Small-3.2-24B-Instruct-2506-MP-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf steampunque/Mistral-Small-3.2-24B-Instruct-2506-MP-GGUF
# Run inference directly in the terminal:
llama cli -hf steampunque/Mistral-Small-3.2-24B-Instruct-2506-MP-GGUF

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 steampunque/Mistral-Small-3.2-24B-Instruct-2506-MP-GGUF
# Run inference directly in the terminal:
./llama-cli -hf steampunque/Mistral-Small-3.2-24B-Instruct-2506-MP-GGUF

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 steampunque/Mistral-Small-3.2-24B-Instruct-2506-MP-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf steampunque/Mistral-Small-3.2-24B-Instruct-2506-MP-GGUF

Use Docker

docker model run hf.co/steampunque/Mistral-Small-3.2-24B-Instruct-2506-MP-GGUF

LM Studio
Jan
Ollama
How to use steampunque/Mistral-Small-3.2-24B-Instruct-2506-MP-GGUF with Ollama:
```
ollama run hf.co/steampunque/Mistral-Small-3.2-24B-Instruct-2506-MP-GGUF
```
Unsloth Desktop
Docker Model Runner
How to use steampunque/Mistral-Small-3.2-24B-Instruct-2506-MP-GGUF with Docker Model Runner:
```
docker model run hf.co/steampunque/Mistral-Small-3.2-24B-Instruct-2506-MP-GGUF
```

Lemonade

How to use steampunque/Mistral-Small-3.2-24B-Instruct-2506-MP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull steampunque/Mistral-Small-3.2-24B-Instruct-2506-MP-GGUF

Run and chat with the model

lemonade run user.Mistral-Small-3.2-24B-Instruct-2506-MP-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

steampunque commited on Feb 18

Commit

34d861b

verified ·

1 Parent(s): 33d2e39

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -10,7 +10,7 @@ tags:
 - 4-bit
 ---
-## Llama.cpp hybrid layer quantization of Mistral-Small-3.2-24B-Instruct-2506 by mistralai
 Original model: https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506
@@ -55,8 +55,8 @@ A full set of benchmarks for the model will eventually be given here: https://hu
 ## Download the file from below:
 | Link | Type | Size/e9 B | Notes |
 |------|------|-----------|-------|
-| [Mistral-Small-3.2-24B-Instruct-2506.Q4_K_H.gguf](https://huggingface.co/steampunque/Mistral-Small-3.2-24B-Instruct-2506-Hybrid-GGUF/resolve/main/Mistral-Small-3.2-24B-Instruct-2506.Q4_K_H.gguf) | Q4_K_H | 12.7e9 B | ~IQ4_XS quality/size |
-| [Mistral-Small-3.2-24B-Instruct-2506.mmproj.gguf](https://huggingface.co/steampunque/Mistral-Small-3.2-24B-Instruct-2506-Hybrid-GGUF/resolve/main/Mistral-Small-3.2-24B-Instruct-2506.mmproj.gguf) | mmproj | 0.88e9 B | multimedia projector |
 A discussion thread about the hybrid layer quant approach can be found here on the llama.cpp git repository:

 - 4-bit
 ---
+## Mixed Precision GGUF layer quantization of Mistral-Small-3.2-24B-Instruct-2506 by mistralai
 Original model: https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506
 ## Download the file from below:
 | Link | Type | Size/e9 B | Notes |
 |------|------|-----------|-------|
+| [Mistral-Small-3.2-24B-Instruct-2506.Q4_K_H.gguf](https://huggingface.co/steampunque/Mistral-Small-3.2-24B-Instruct-2506-MP-GGUF/resolve/main/Mistral-Small-3.2-24B-Instruct-2506.Q4_K_H.gguf) | Q4_K_H | 12.7e9 B | ~IQ4_XS quality/size |
+| [Mistral-Small-3.2-24B-Instruct-2506.mmproj.gguf](https://huggingface.co/steampunque/Mistral-Small-3.2-24B-Instruct-2506-MP-GGUF/resolve/main/Mistral-Small-3.2-24B-Instruct-2506.mmproj.gguf) | mmproj | 0.88e9 B | multimedia projector |
 A discussion thread about the hybrid layer quant approach can be found here on the llama.cpp git repository: