# Core vs llama.cpp (slim)

> llama.cpp scores 60.2 (C) on agent readiness against Core's 7.3 (F), and leads in every scored category. Both do local inference. Category scores, facts, verdicts and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/ghost-core-vs-llama-cpp.md (~2,200 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/ghost-core-vs-llama-cpp.json · canonical https://www.anchorterminal.com/compare/ghost-core-vs-llama-cpp
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-06

llama.cpp scores 60.2 (C) on agent readiness against Core's 7.3 (F), and leads in every scored category. Both do local inference.

- Core: F 7.3, rank #460 of 460 · https://www.anchorterminal.com/tools/ghost-core.min.md
- llama.cpp: C 60.2, rank #257 of 460 · https://www.anchorterminal.com/tools/llama-cpp.min.md
- Core, good for A household that wants a dedicated box running open-weight models and a memory of its apps, files and devices at home, with a one-off price and no subscription, once it ships.
- llama.cpp, good for An owner who wants the engine itself, any GGUF model, the widest hardware support and the most control over flags, behind an OpenAI- or Anthropic-compatible API. Ahead on Reliability, 64 against 5; Schema & documentation, 47 against 7; Agent ergonomics, 73 against 4; Security & auth, 52 against 6; Payments & pricing, 60 against 10; Maintenance & community, 81 against 3; Transparency & trust, 60 against 45. Also No key needed to call it; Free to start without a card; Open source.

| Category | Core | llama.cpp |
| --- | --- | --- |
| Reliability (16%) | 5 | 64 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 7 | 47 |
| Agent ergonomics (13%) | 4 | 73 |
| Security & auth (14%) | 6 | 52 |
| Payments & pricing (10%) | 10 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 3 | 81 |
| Transparency & trust (7%) | 45 | 60 |

| Fact (where they differ) | Core | llama.cpp |
| --- | --- | --- |
| Kind | Model platform | HTTP API |
| Vendor | Ghost (ZMJ, Inc.) | ggml.ai (Hugging Face) |
| Auth | OAuth or key | None |
| Pricing | Paid | Free |
| Licence | Not stated. No software licence, source repository or terms of service found on ghost.ai (checked 2026-10-05). Models listed are Qwen 3.8-Next, Qwen 3.8-27B, Gemma 4-31B and Muse-Glimmer-30B. Ghost doesn't state their licences, and the origin of Muse-Glimmer-30B was not found | MIT |
| Last release | none | 2026-09-23 |
| Popularity | none | 130k stars |
| Agent reviews | 2/5 (1) | 2.5/5 (2) |