Instructions to use prithivMLmods/palmyra-mini-thinking-AIO-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/palmyra-mini-thinking-AIO-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="prithivMLmods/palmyra-mini-thinking-AIO-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/palmyra-mini-thinking-AIO-GGUF", dtype="auto")

llama-cpp-python

How to use prithivMLmods/palmyra-mini-thinking-AIO-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="prithivMLmods/palmyra-mini-thinking-AIO-GGUF",
	filename="palmyra-mini-GGUF/palmyra-mini.BF16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use prithivMLmods/palmyra-mini-thinking-AIO-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf prithivMLmods/palmyra-mini-thinking-AIO-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/palmyra-mini-thinking-AIO-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf prithivMLmods/palmyra-mini-thinking-AIO-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/palmyra-mini-thinking-AIO-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 prithivMLmods/palmyra-mini-thinking-AIO-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/palmyra-mini-thinking-AIO-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 prithivMLmods/palmyra-mini-thinking-AIO-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/palmyra-mini-thinking-AIO-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/palmyra-mini-thinking-AIO-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use prithivMLmods/palmyra-mini-thinking-AIO-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/palmyra-mini-thinking-AIO-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/palmyra-mini-thinking-AIO-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/palmyra-mini-thinking-AIO-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/palmyra-mini-thinking-AIO-GGUF 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 "prithivMLmods/palmyra-mini-thinking-AIO-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/palmyra-mini-thinking-AIO-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "prithivMLmods/palmyra-mini-thinking-AIO-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/palmyra-mini-thinking-AIO-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use prithivMLmods/palmyra-mini-thinking-AIO-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/palmyra-mini-thinking-AIO-GGUF:Q4_K_M
```

Unsloth Studio new

How to use prithivMLmods/palmyra-mini-thinking-AIO-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 prithivMLmods/palmyra-mini-thinking-AIO-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 prithivMLmods/palmyra-mini-thinking-AIO-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for prithivMLmods/palmyra-mini-thinking-AIO-GGUF to start chatting

Docker Model Runner
How to use prithivMLmods/palmyra-mini-thinking-AIO-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/palmyra-mini-thinking-AIO-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/palmyra-mini-thinking-AIO-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/palmyra-mini-thinking-AIO-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.palmyra-mini-thinking-AIO-GGUF-Q4_K_M

List all available models

lemonade list

palmyra-mini-thinking-AIO-GGUF

The palmyra-mini models demonstrates exceptional capabilities in complex reasoning and mathematical problem-solving domains. Its performance is particularly noteworthy on benchmarks that require deep understanding and multi-step thought processes. A key strength of the model is its proficiency in grade-school-level math problems, as evidenced by its impressive score of 0.818 on the gsm8k (strict-match) benchmark. This high score indicates a robust ability to parse and solve word problems, a foundational skill for more advanced quantitative reasoning. This aptitude for mathematics is further confirmed by its outstanding performance on the MATH500 benchmark, where it also achieved a score of 0.818. This result underscores the models consistent and reliable mathematical capabilities across different problem sets. The model also shows strong performance on the AMC23 benchmark, with a solid score of 0.6. This benchmark, representing problems from the American Mathematics Competitions, highlights the models ability to tackle challenging, competition-level mathematics.

Palmyra Mini GGUF Variants

Model Name	Download Link
palmyra-mini-GGUF	Link
palmyra-mini-thinking-a-GGUF	Link
palmyra-mini-thinking-b-GGUF	Link

Model Files

palmyra-mini

File Name	Quant Type	File Size
palmyra-mini.BF16.gguf	BF16	3.56 GB
palmyra-mini.F16.gguf	F16	3.56 GB
palmyra-mini.F32.gguf	F32	7.11 GB
palmyra-mini.Q2_K.gguf	Q2_K	752 MB
palmyra-mini.Q3_K_L.gguf	Q3_K_L	980 MB
palmyra-mini.Q3_K_M.gguf	Q3_K_M	924 MB
palmyra-mini.Q3_K_S.gguf	Q3_K_S	861 MB
palmyra-mini.Q4_0.gguf	Q4_0	1.07 GB
palmyra-mini.Q4_1.gguf	Q4_1	1.16 GB
palmyra-mini.Q4_K.gguf	Q4_K	1.12 GB
palmyra-mini.Q4_K_M.gguf	Q4_K_M	1.12 GB
palmyra-mini.Q4_K_S.gguf	Q4_K_S	1.07 GB
palmyra-mini.Q5_0.gguf	Q5_0	1.26 GB
palmyra-mini.Q5_1.gguf	Q5_1	1.35 GB
palmyra-mini.Q5_K.gguf	Q5_K	1.28 GB
palmyra-mini.Q5_K_M.gguf	Q5_K_M	1.28 GB
palmyra-mini.Q5_K_S.gguf	Q5_K_S	1.26 GB
palmyra-mini.Q6_K.gguf	Q6_K	1.46 GB
palmyra-mini.Q8_0.gguf	Q8_0	1.89 GB

palmyra-mini-thinking-a

File Name	Quant Type	File Size
palmyra-mini-thinking-a.BF16.gguf	BF16	3.56 GB
palmyra-mini-thinking-a.F16.gguf	F16	3.56 GB
palmyra-mini-thinking-a.F32.gguf	F32	7.11 GB
palmyra-mini-thinking-a.Q2_K.gguf	Q2_K	752 MB
palmyra-mini-thinking-a.Q3_K_L.gguf	Q3_K_L	980 MB
palmyra-mini-thinking-a.Q3_K_M.gguf	Q3_K_M	924 MB
palmyra-mini-thinking-a.Q3_K_S.gguf	Q3_K_S	861 MB
palmyra-mini-thinking-a.Q4_0.gguf	Q4_0	1.07 GB
palmyra-mini-thinking-a.Q4_1.gguf	Q4_1	1.16 GB
palmyra-mini-thinking-a.Q4_K.gguf	Q4_K	1.12 GB
palmyra-mini-thinking-a.Q4_K_M.gguf	Q4_K_M	1.12 GB
palmyra-mini-thinking-a.Q4_K_S.gguf	Q4_K_S	1.07 GB
palmyra-mini-thinking-a.Q5_0.gguf	Q5_0	1.26 GB
palmyra-mini-thinking-a.Q5_1.gguf	Q5_1	1.35 GB
palmyra-mini-thinking-a.Q5_K.gguf	Q5_K	1.28 GB
palmyra-mini-thinking-a.Q5_K_M.gguf	Q5_K_M	1.28 GB
palmyra-mini-thinking-a.Q5_K_S.gguf	Q5_K_S	1.26 GB
palmyra-mini-thinking-a.Q6_K.gguf	Q6_K	1.46 GB
palmyra-mini-thinking-a.Q8_0.gguf	Q8_0	1.89 GB

palmyra-mini-thinking-b

File Name	Quant Type	File Size
palmyra-mini-thinking-b.BF16.gguf	BF16	3.09 GB
palmyra-mini-thinking-b.F16.gguf	F16	3.09 GB
palmyra-mini-thinking-b.F32.gguf	F32	6.18 GB
palmyra-mini-thinking-b.Q2_K.gguf	Q2_K	676 MB
palmyra-mini-thinking-b.Q3_K_L.gguf	Q3_K_L	880 MB
palmyra-mini-thinking-b.Q3_K_M.gguf	Q3_K_M	824 MB
palmyra-mini-thinking-b.Q3_K_S.gguf	Q3_K_S	761 MB
palmyra-mini-thinking-b.Q4_0.gguf	Q4_0	935 MB
palmyra-mini-thinking-b.Q4_1.gguf	Q4_1	1.02 GB
palmyra-mini-thinking-b.Q4_K.gguf	Q4_K	986 MB
palmyra-mini-thinking-b.Q4_K_M.gguf	Q4_K_M	986 MB
palmyra-mini-thinking-b.Q4_K_S.gguf	Q4_K_S	940 MB
palmyra-mini-thinking-b.Q5_0.gguf	Q5_0	1.1 GB
palmyra-mini-thinking-b.Q5_1.gguf	Q5_1	1.18 GB
palmyra-mini-thinking-b.Q5_K.gguf	Q5_K	1.13 GB
palmyra-mini-thinking-b.Q5_K_M.gguf	Q5_K_M	1.13 GB
palmyra-mini-thinking-b.Q5_K_S.gguf	Q5_K_S	1.1 GB
palmyra-mini-thinking-b.Q6_K.gguf	Q6_K	1.27 GB
palmyra-mini-thinking-b.Q8_0.gguf	Q8_0	1.65 GB

Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

Downloads last month: 155

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

32-bit

Model tree for prithivMLmods/palmyra-mini-thinking-AIO-GGUF

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Writer/palmyra-mini

Quantized

(5)

this model