Instructions to use python-processing-unit/Supra-50M-Reasoning-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use python-processing-unit/Supra-50M-Reasoning-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="python-processing-unit/Supra-50M-Reasoning-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("python-processing-unit/Supra-50M-Reasoning-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use python-processing-unit/Supra-50M-Reasoning-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 python-processing-unit/Supra-50M-Reasoning-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf python-processing-unit/Supra-50M-Reasoning-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf python-processing-unit/Supra-50M-Reasoning-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf python-processing-unit/Supra-50M-Reasoning-GGUF:F16

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 python-processing-unit/Supra-50M-Reasoning-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf python-processing-unit/Supra-50M-Reasoning-GGUF:F16

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 python-processing-unit/Supra-50M-Reasoning-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf python-processing-unit/Supra-50M-Reasoning-GGUF:F16

Use Docker

docker model run hf.co/python-processing-unit/Supra-50M-Reasoning-GGUF:F16

LM Studio
Jan

vLLM

How to use python-processing-unit/Supra-50M-Reasoning-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "python-processing-unit/Supra-50M-Reasoning-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "python-processing-unit/Supra-50M-Reasoning-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/python-processing-unit/Supra-50M-Reasoning-GGUF:F16

SGLang

How to use python-processing-unit/Supra-50M-Reasoning-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 "python-processing-unit/Supra-50M-Reasoning-GGUF" \
    --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": "python-processing-unit/Supra-50M-Reasoning-GGUF",
		"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 "python-processing-unit/Supra-50M-Reasoning-GGUF" \
        --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": "python-processing-unit/Supra-50M-Reasoning-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use python-processing-unit/Supra-50M-Reasoning-GGUF with Ollama:
```
ollama run hf.co/python-processing-unit/Supra-50M-Reasoning-GGUF:F16
```
Unsloth Desktop
Docker Model Runner
How to use python-processing-unit/Supra-50M-Reasoning-GGUF with Docker Model Runner:
```
docker model run hf.co/python-processing-unit/Supra-50M-Reasoning-GGUF:F16
```

Lemonade

How to use python-processing-unit/Supra-50M-Reasoning-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull python-processing-unit/Supra-50M-Reasoning-GGUF:F16

Run and chat with the model

lemonade run user.Supra-50M-Reasoning-GGUF-F16

List all available models

lemonade list

Atomic Chat

python-processing-unit commited on Jun 16

Commit

94addc4

verified ·

1 Parent(s): 12ee526

Upload folder using huggingface_hub

Browse files

Files changed (4) hide show

.gitattributes +2 -0
README.md +46 -3
supra-50m-reasoning-f16.gguf +3 -0
supra-50m-reasoning-q8_0.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+supra-50m-reasoning-f16.gguf filter=lfs diff=lfs merge=lfs -text
+supra-50m-reasoning-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -1,3 +1,46 @@
----
-license: apache-2.0
----

+---
+license: apache-2.0
+datasets:
+- HuggingFaceFW/fineweb-edu
+- SupraLabs/SupraThink-Dataset-500x
+language:
+- en
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- supra
+- chimera
+- 50m
+- llama
+- small
+- open
+- open-source
+- cpu
+- tiny
+- slm
+- reasoning
+- think
+- thinking
+base_model:
+- SupraLabs/Supra-50M-Reasoning
+---
+# Supra-50M-Reasoning GGUF
+This is a GGUF export of [**Supra-50M-Reasoning**](https://huggingface.co/SupraLabs/Supra-50M-Reasoning).
+---
+## Quants
+Includes both a f16 and a q8_0 quantization.
+---
+## License
+This model is released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0).
+---
+*© SupraLabs 2026 — Project Chimera*

supra-50m-reasoning-f16.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:79d4584186d0e1373f3baeb7e43025355f5fdc351276ae6998cade39088cb356
+size 104740672

supra-50m-reasoning-q8_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e6fd6d64a4664e054b202111683062d051d21ec91ab56aaf93e5b1545bda07a0
+size 56203072