The home of open models, datasets and Spaces.
llama.cpp
Runs LLMs locally in C/C++ on CPUs and GPUs.
SharkScore
#10 in Model APIs & inference
Why it scores 72.1
llama.cpp has a SharkScore of 72.1/100, ranked #10 of 262 in Model APIs & inference (updated 2026-11-18).
Each part compares llama.cpp with other listings in Model APIs & inference. Evidence covers 87% of the score's weight.
- Adoption
- 57 · 30%
- User reviews
- no data · 25%
- Maintenance
- 100 · 20%
- Trust & transparency
- 80 · 15%
- Momentum
- no data · 10%
Paying never changes this score. How ranking works · method v2026-11-18.2
RankShark review of llama.cpp
Automated evaluation by RankShark · 18 Nov 2026 · method v1.0 · How we review
We were not paid for this review.
As of 2026-11-18, llama.cpp is an MIT-licensed C/C++ inference project with a command-line interface and an OpenAI-compatible API server. [E1]
llama.cpp is a C/C++ project for running LLM and multimodal LLM inference locally or in the cloud. Its README includes a command-line tool and an OpenAI-compatible API server. [E1]
Best for
Not for
- Teams that require stated data-retention, data-region, or DPA terms; these are not stated on the supplied project page. · home page
Key features
- LLM and multimodal inference. The vendor says the project enables LLM and MLLM inference locally and in the cloud. · home page
- Hardware range. The vendor says it targets a wide range of hardware. · home page
- Command-line interface. The vendor provides a CLI, including a quick-start command that downloads and runs a model from Hugging Face. · home page
- API server. The vendor says llama serve launches an OpenAI-compatible API server. · home page
- Additional tools. The vendor lists completion, server, text-to-speech model, and GBNF grammar tools. · home page
- License. The repository lists an MIT license. · home page
Pros
Cons
- The supplied project page does not state pricing, data-retention terms, data regions, or a DPA. · home page
- No public prices found on the pages we checked. · pricing page
- No free plan or free trial stated on the pages we checked.
- Whether customer data is used for model training is not stated on the pages we checked.
- Free plan
- Not stated (checked 18 Nov 2026)
- Free trial
- Not stated (checked 18 Nov 2026)
- Trains on customer data
- Not stated (checked 18 Nov 2026)
- Data retention
- Not stated (checked 18 Nov 2026)
- Data regions
- Not stated (checked 18 Nov 2026)
- Data processing agreement
- Not stated (checked 18 Nov 2026)
- AI models used
- The README quick-start example uses ggml-org/Qwen3.5-0.8B-GGUF. · home page
- API
- llama serve launches an OpenAI-compatible API server. · home page
- SDKs
- Not stated (checked 18 Nov 2026)
- Webhooks
- Not stated (checked 18 Nov 2026)
- Platforms
- The README describes local and cloud inference, Docker usage, and an Android build guide. · home page
- Security claims
- No security certification stated (checked 18 Nov 2026)
What we measured
- GitHub stars · now
- 135,691
- Latest release · now
- v1.0.0 on 2026-11-13
How we tested · sources
- Hourly uptime and response-time checks of the product's URL.
- Repository, release and download data from GitHub, npm, PyPI and Hugging Face where they exist.
- We did not sign up, pay, or use the product as a customer.
- home page: https://github.com/ggml-org/llama.cpp · fetched 18 Nov 2026
- pricing page: https://github.com/pricing · fetched 18 Nov 2026
- docs: https://docs.github.com/en · fetched 18 Nov 2026
- changelog: https://github.com/ggml-org/llama.cpp/releases?q=tag:v1 · fetched 18 Nov 2026 · blocked our checker
- privacy page: https://docs.github.com/en/site-policy/privacy-policies/github-general-privacy-statement · fetched 18 Nov 2026
- terms: https://docs.github.com/en/site-policy/github-terms/github-terms-of-service · fetched 18 Nov 2026
- security page: https://github.com/security/advanced-security/code-security · fetched 18 Nov 2026
Something wrong? Report an error with a public link that shows it; corrections re-run the review.
Top alternatives to llama.cpp
See all- 78.9ToolFreemium · from $9/mo
- 77.5
API for building with Claude models.
ToolPaid - 76.1
Proxy and SDK to call 100+ LLM APIs in the OpenAI format.
ToolOpen source - 75.7
Google Cloud's platform to build with Gemini and other models.
ToolPaid