Instructions to use starble-dev/Nemo-12B-Marlin-v5-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use starble-dev/Nemo-12B-Marlin-v5-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("starble-dev/Nemo-12B-Marlin-v5-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use starble-dev/Nemo-12B-Marlin-v5-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 starble-dev/Nemo-12B-Marlin-v5-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf starble-dev/Nemo-12B-Marlin-v5-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf starble-dev/Nemo-12B-Marlin-v5-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf starble-dev/Nemo-12B-Marlin-v5-GGUF:Q4_K_M

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 starble-dev/Nemo-12B-Marlin-v5-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf starble-dev/Nemo-12B-Marlin-v5-GGUF:Q4_K_M

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 starble-dev/Nemo-12B-Marlin-v5-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf starble-dev/Nemo-12B-Marlin-v5-GGUF:Q4_K_M

Use Docker

docker model run hf.co/starble-dev/Nemo-12B-Marlin-v5-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use starble-dev/Nemo-12B-Marlin-v5-GGUF with Ollama:
```
ollama run hf.co/starble-dev/Nemo-12B-Marlin-v5-GGUF:Q4_K_M
```

Unsloth Studio

How to use starble-dev/Nemo-12B-Marlin-v5-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 starble-dev/Nemo-12B-Marlin-v5-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 starble-dev/Nemo-12B-Marlin-v5-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for starble-dev/Nemo-12B-Marlin-v5-GGUF to start chatting

Docker Model Runner
How to use starble-dev/Nemo-12B-Marlin-v5-GGUF with Docker Model Runner:
```
docker model run hf.co/starble-dev/Nemo-12B-Marlin-v5-GGUF:Q4_K_M
```

Lemonade

How to use starble-dev/Nemo-12B-Marlin-v5-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull starble-dev/Nemo-12B-Marlin-v5-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Nemo-12B-Marlin-v5-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

General Use Sampling:
Mistral-Nemo-12B is very sensitive to the temperature sampler, try values near 0.3 at first or else you will get some weird results. This is mentioned by MistralAI at their Transformers section.

Best Samplers:
I found best success using the following for Nemo-12B-Marlin-v5:
Temperature: 0.7-0.8
Top K: -1
Min P: 0.05
Rep Penalty: 1.03 (Note, it is recommended to increase this as context length increases, I find 1.10 to be good at 16k+ context)

Currently this is my favorite Mistral-Nemo finetune to be released.

Original Model: UsernameJustAnother/Nemo-12B-Marlin-v5 (Thank you so much for your work ♥)

Official Quants: UsernameJustAnother/Nemo-12B-Marlin-v5-gguf (Currently only Q8_0)

How to Use: llama.cpp

Original Model License: Apache 2.0

Release Used: b3538

Quants

PPL = Perplexity, lower is better
Comparisons are done as QX_X Llama-3-8B against FP16 Llama-3-8B, recommended as a guideline and not as fact.

Quant Type	Note	Size
Q2_K	+3.5199 ppl @ Llama-3-8B	4.79 GB
Q3_K_S	+1.6321 ppl @ Llama-3-8B	5.53 GB
Q3_K_M	+0.6569 ppl @ Llama-3-8B	6.08 GB
Q3_K_L	+0.5562 ppl @ Llama-3-8B	6.56 GB
Q4_K_S	+0.2689 ppl @ Llama-3-8B	7.12 GB
Q4_K_M	+0.1754 ppl @ Llama-3-8B	7.48 GB
Q5_K_S	+0.1049 ppl @ Llama-3-8B	8.52 GB
Q5_K_M	+0.0569 ppl @ Llama-3-8B	8.73 GB
Q6_K	+0.0217 ppl @ Llama-3-8B	10.1 GB
Q8_0	+0.0026 ppl @ Llama-3-8B	13.00 GB

Downloads last month: 148

GGUF

Model size

12B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for starble-dev/Nemo-12B-Marlin-v5-GGUF

Base model

unsloth/Mistral-Nemo-Instruct-2407

Finetuned

UsernameJustAnother/Nemo-12B-Marlin-v5

Quantized

(2)

this model

starble-dev
/

Nemo-12B-Marlin-v5-GGUF

Quants

Model tree for starble-dev/Nemo-12B-Marlin-v5-GGUF

Space using starble-dev/Nemo-12B-Marlin-v5-GGUF 1