shamily/gemma4-llama-dgx-spark

Dockerized inference server and benchmarks for Gemma 4 26B on the NVIDIA DGX Spark (GB10). Features ARM64 CUDA 13 builds using llama.cpp.

/ 100

Experimental

No Package No Dependents

Maintenance 13 / 25

Adoption 0 / 25

Maturity 9 / 25

Community 0 / 25

Stars

—

Forks

—

Language

Shell

License

MIT

Last pushed

Apr 06, 2026

Commits (30d)

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/shamily/gemma4-llama-dgx-spark"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Higher-rated alternatives

campfirein/byterover-cli

ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher)

mistralai/client-python

Python client library for Mistral AI platform

openai/openai-python

The official Python library for the OpenAI API

pydantic/pydantic

Data validation using Python type hints

milla-jovovich/mempalace

The highest-scoring AI memory system ever benchmarked. And it's free.