Instructions to use unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF",
	filename="Mistral-Small-3.1-24B-Instruct-2503-BF16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/Mistral-Small-3.1-24B-Instruct-2503-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/Mistral-Small-3.1-24B-Instruct-2503-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/Mistral-Small-3.1-24B-Instruct-2503-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/Mistral-Small-3.1-24B-Instruct-2503-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/Mistral-Small-3.1-24B-Instruct-2503-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/Mistral-Small-3.1-24B-Instruct-2503-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/Mistral-Small-3.1-24B-Instruct-2503-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/Mistral-Small-3.1-24B-Instruct-2503-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF:UD-Q4_K_XL

LM Studio
Jan
Ollama
How to use unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF with Ollama:
```
ollama run hf.co/unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use unsloth/Mistral-Small-3.1-24B-Instruct-2503-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/Mistral-Small-3.1-24B-Instruct-2503-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/Mistral-Small-3.1-24B-Instruct-2503-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/Mistral-Small-3.1-24B-Instruct-2503-GGUF to start chatting

Docker Model Runner
How to use unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Mistral-Small-3.1-24B-Instruct-2503-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Inference does not run using Ollama 0.6.8 – Mistral-Small-3.1-24B-Instruct-2503-GGUF:Q4_K_M

by deleted - opened May 10, 2025

Discussion

deleted

May 10, 2025

Hi there, I'm fairly new to LLMs, but this quantisation doesn't seem to run using Ollama 0.6.8 [MacBook Air M4 32GB, macOS 15.4.1]:
Error: llama runner process has terminated: exit status 2

Relevant output from server log:

clip_model_loader: tensor[220]: n_dims = 2, name = v.blk.9.ffn_gate.weight, tensor_size=8388608, offset=861257728, shape:[1024, 4096, 1, 1], type = f16 clip_model_loader: tensor[221]: n_dims = 2, name = v.blk.9.ffn_up.weight, tensor_size=8388608, offset=869646336, shape:[1024, 4096, 1, 1], type = f16 clip_model_loader: tensor[222]: n_dims = 1, name = v.blk.9.ln2.weight, tensor_size=4096, offset=878034944, shape:[1024, 1, 1, 1], type = f32 load_hparams: projector: pixtral load_hparams: has_llava_proj: 0 load_hparams: minicpmv_version: 0 load_hparams: proj_scale_factor: 0 load_hparams: n_wa_pattern: 0 load_hparams: use_silu: 1 load_hparams: use_gelu: 0 load_hparams: model size: 837.36 MiB load_hparams: metadata size: 0.08 MiB clip_init: failed to load model '/Users/user/.ollama/models/blobs/sha256-402640c0a0e4e00cdb1e94349adf7c2289acab05fee2b20ee635725ef588f994': operator(): unable to find tensor mm.1.bias

ggml_metal_free: deallocating panic: unable to load clip model: /Users/user/.ollama/models/blobs/sha256-402640c0a0e4e00cdb1e94349adf7c2289acab05fee2b20ee635725ef588f994

goroutine 37 [running]: github.com/ollama/ollama/runner/llamarunner.(*Server).loadModel(0x14000176360, {0x29, 0x0 , 0x1, 0x0, {0x0, 0x0, 0x0}, 0x140004a7a10, 0x0}, ...) /Users/runner/work/ollama/ollama/runner/llamarunner/runner.go:795 +0x264 created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1 /Users/runner/work/ollama/ollama/runner/llamarunner/runner.go:887 +0x994 time=2025-05-10T12:24:32.056+10:00 level=INFO source=server.go:623 msg="waiting for server to become available" status="llm server not responding" time=2025-05-10T12:24:32.307+10:00 level=ERROR source=sched.go:458 msg="error loading llama server" error="llama runner process has terminated: exit status 2"

Thank you!

deleted changed discussion title from Inference does not run using Ollama – Mistral-Small-3.1-24B-Instruct-2503-GGUF:Q4_K_M to Inference does not run using Ollama 0.6.8 – Mistral-Small-3.1-24B-Instruct-2503-GGUF:Q4_K_M May 10, 2025

deleted

May 10, 2025

Edit: Sorry, just saw an update in the other discussion – issue may be caused by Ollama not using latest PR llama.cpp
https://huggingface.co/unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF/discussions/2#681def7f67aec79d34b39d8f

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment