Instructions to use appvoid/palmer-006 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use appvoid/palmer-006 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="appvoid/palmer-006")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("appvoid/palmer-006")
model = AutoModelForCausalLM.from_pretrained("appvoid/palmer-006", device_map="auto")

llama-cpp-python

How to use appvoid/palmer-006 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="appvoid/palmer-006",
	filename="model.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use appvoid/palmer-006 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 appvoid/palmer-006
# Run inference directly in the terminal:
llama cli -hf appvoid/palmer-006

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf appvoid/palmer-006
# Run inference directly in the terminal:
llama cli -hf appvoid/palmer-006

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 appvoid/palmer-006
# Run inference directly in the terminal:
./llama-cli -hf appvoid/palmer-006

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 appvoid/palmer-006
# Run inference directly in the terminal:
./build/bin/llama-cli -hf appvoid/palmer-006

Use Docker

docker model run hf.co/appvoid/palmer-006

LM Studio
Jan

vLLM

How to use appvoid/palmer-006 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "appvoid/palmer-006"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "appvoid/palmer-006",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/appvoid/palmer-006

SGLang

How to use appvoid/palmer-006 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "appvoid/palmer-006" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "appvoid/palmer-006",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "appvoid/palmer-006" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "appvoid/palmer-006",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use appvoid/palmer-006 with Ollama:
```
ollama run hf.co/appvoid/palmer-006
```

Unsloth Studio

How to use appvoid/palmer-006 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 appvoid/palmer-006 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 appvoid/palmer-006 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for appvoid/palmer-006 to start chatting

Atomic Chat new
Docker Model Runner
How to use appvoid/palmer-006 with Docker Model Runner:
```
docker model run hf.co/appvoid/palmer-006
```

Lemonade

How to use appvoid/palmer-006 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull appvoid/palmer-006

Run and chat with the model

lemonade run user.palmer-006-{{QUANT_TAG}}

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

You agree to use this model in good faith, respect the LICENSE in this repository, comply with the applicable Falcon upstream terms, and not use the model to harm any person or group. Commercial use requires a separate license.

a small model is all you need

We celebrate three years of experiments with the release of palmer-006, our flagship and extremely small language model for local experimentation, edge hardware, small SBCs, and low-power devices. Note that this model serves primarily as a language model and has not been validated nor finetuned as a general-purpose chat assistant. Thus further finetuning is required to properly work as an instruction-tuned model.

● details

🥈 As of 07/26/26, it takes the 2nd spot on ArithMark-3, only behind MobileLLM-R1-140M-base, while being 36% smaller. It also took second spot on BananaMindBench Leaderboard!!🎉🎉

Palmer 006 benchmark comparison

We first lightly fine-tuned the base model on a diverse set of highly curated data points. We then “palmerized” it by merging models, followed by another light fine-tuning round. Finally, we adjusted Mamba for maximum token speed. With only 90M parameters, this turned the model into a competitive baseline against models above 125M parameters.

As seen in the benchmark, we are getting closer to the performance of bigger models with our current technique, even on models of this size. Note: We used acc_norm whenever available.

● quick test

You can load model.gguf model into a llama-server, then run the script inside this repo as follows:

python completion.py prompt.txt

● license

Open research, education, hobby use, modification, and redistribution are permitted. Commercial deployment, internal business use, paid products, hosted APIs, and client work require a separate commercial license from appvoid. For commercial licensing: nosoyhackercodigo@gmail.com

👋 But hey! If you already have a donation subscription, you can claim access to a free commercial license through the email above. You will keep the rights as long as the subscription is active.

● upstream attribution

palmer-006 is built using artificial intelligence technology from the Technology Innovation Institute.

● fun facts

the new logo represents palmer's eye, pointing how small this new model is
palmer models still exists to some extent due to inspiration from Karpathy's idea of a self-contained "cognitive core".
we just like light finetuning because we prefer starting "real" experiments with the strongest baseline possible

Downloads last month: 60

Safetensors

Model size

91.1M params

Tensor type

BF16

Collection including appvoid/palmer-006

latest releases

Collection

2 items • Updated 1 day ago