Instructions to use sahilchachra/supra-50m-instruct-fp16-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sahilchachra/supra-50m-instruct-fp16-mlx with MLX:

# Download the model from the Hub
pip install huggingface_hub[hf_xet]

huggingface-cli download --local-dir supra-50m-instruct-fp16-mlx sahilchachra/supra-50m-instruct-fp16-mlx

llama-cpp-python

How to use sahilchachra/supra-50m-instruct-fp16-mlx with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="sahilchachra/supra-50m-instruct-fp16-mlx",
	filename="Supra-50M-f16.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 sahilchachra/supra-50m-instruct-fp16-mlx 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 sahilchachra/supra-50m-instruct-fp16-mlx:F16
# Run inference directly in the terminal:
llama cli -hf sahilchachra/supra-50m-instruct-fp16-mlx:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf sahilchachra/supra-50m-instruct-fp16-mlx:F16
# Run inference directly in the terminal:
llama cli -hf sahilchachra/supra-50m-instruct-fp16-mlx: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 sahilchachra/supra-50m-instruct-fp16-mlx:F16
# Run inference directly in the terminal:
./llama-cli -hf sahilchachra/supra-50m-instruct-fp16-mlx: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 sahilchachra/supra-50m-instruct-fp16-mlx:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sahilchachra/supra-50m-instruct-fp16-mlx:F16

Use Docker

docker model run hf.co/sahilchachra/supra-50m-instruct-fp16-mlx:F16

LM Studio
Jan
Ollama
How to use sahilchachra/supra-50m-instruct-fp16-mlx with Ollama:
```
ollama run hf.co/sahilchachra/supra-50m-instruct-fp16-mlx:F16
```

Unsloth Studio

How to use sahilchachra/supra-50m-instruct-fp16-mlx 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 sahilchachra/supra-50m-instruct-fp16-mlx 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 sahilchachra/supra-50m-instruct-fp16-mlx to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sahilchachra/supra-50m-instruct-fp16-mlx to start chatting

Atomic Chat new
Docker Model Runner
How to use sahilchachra/supra-50m-instruct-fp16-mlx with Docker Model Runner:
```
docker model run hf.co/sahilchachra/supra-50m-instruct-fp16-mlx:F16
```

Lemonade

How to use sahilchachra/supra-50m-instruct-fp16-mlx with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sahilchachra/supra-50m-instruct-fp16-mlx:F16

Run and chat with the model

lemonade run user.supra-50m-instruct-fp16-mlx-F16

List all available models

lemonade list

supra-50m-instruct-fp16-mlx

MLX quantization of SupraLabs/Supra-50M-Instruct for Apple Silicon.

Variant: BFloat16 (lossless reference)
Disk size: 201 MB
Quantized by: sahilchachra

Benchmark results

Evaluated on Apple M4 Pro with MLX. Model loaded once; performance and quality measured in a single pass.

Performance

	This model	FP16 baseline
Decode tok/s (avg, long traces)	1270.13	1270.13
Peak memory (GB)	0.223	0.223
Disk size (MB)	201	201

Quality

Benchmark	This model	FP16 baseline	n
IFEval (instruction following)	15.9%	15.9%	44
Alpaca-cleaned (instruct F1 vs reference)	36.2	36.2	50

Context scaling (decode tok/s)

Context length	Decode tok/s
~128 tokens	1294.4
~256 tokens	1274.3
~512 tokens	1277.6
~1024 tokens	1234.2

Usage

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("sahilchachra/supra-50m-instruct-fp16-mlx")
response = generate(model, tokenizer, prompt="Your prompt here", max_tokens=256, verbose=True)

All variants in this collection

Model	Variant
sahilchachra/supra-50m-instruct-8bit-mlx	Affine int8
sahilchachra/supra-50m-instruct-optiq-5bpw-mlx	OptiQ mixed-precision (target 5.0 bpw)

Notes

Requires Apple Silicon (M1 or later) with MLX
Benchmarks run on Apple M4 Pro, 24 GB unified memory
License: see SupraLabs/Supra-50M-Instruct for the original model's license

Original model

See SupraLabs/Supra-50M-Instruct for full model details and intended use.

Downloads last month: 138

Safetensors

Model size

51.8M params

Tensor type

BF16

MLX

Hardware compatibility

Quantized

Inference Providers NEW

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

Model tree for sahilchachra/supra-50m-instruct-fp16-mlx

Base model

SupraLabs/Supra-50M-Base

Quantized

SupraLabs/Supra-50M-Instruct

Quantized

(6)

this model

Collection including sahilchachra/supra-50m-instruct-fp16-mlx

Supra 50M Instruct

Collection

4 items • Updated 17 days ago