# Core vs vLLM (slim)

> vLLM scores 57.7 (C) to Core's 7.3 (F) for local inference. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/ghost-core-vs-vllm.md (~2,650 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/ghost-core-vs-vllm.json · canonical https://www.anchorterminal.com/compare/ghost-core-vs-vllm
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

vLLM scores 57.7 (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 #950 of 950 · https://www.anchorterminal.com/tools/ghost-core.min.md
- vLLM: C 57.7, rank #600 of 950 · https://www.anchorterminal.com/tools/vllm.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.
- vLLM, good for An owner with a GPU server who wants many concurrent requests against one open-weight model behind OpenAI or Anthropic compatible routes. Ahead on Reliability, 62 against 5; Schema & documentation, 68 against 7; Agent ergonomics, 64 against 4; Security & auth, 50 against 6; Payments & pricing, 60 against 10; Maintenance & community, 88 against 3; Transparency & trust, 67 against 45. Also No key needed to call it; Free to start without a card; Open source.

| Category | Core | vLLM |
| --- | --- | --- |
| Reliability (16%) | 5 | 62 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 7 | 68 |
| Agent ergonomics (13%) | 4 | 64 |
| Security & auth (14%) | 6 | 50 |
| Payments & pricing (10%) | 10 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 3 | 88 |
| Transparency & trust (7%) | 45 | 67 |

| Fact (where they differ) | Core | vLLM |
| --- | --- | --- |
| Kind | Model platform | HTTP API |
| Vendor | Ghost (ZMJ, Inc.) | vLLM project (PyTorch Foundation) |
| 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 | Apache-2.0 |
| Last release | none | 2026-10-02 |
| Privacy policy last updated | 2026-10-05 | no document linked |
| Popularity | none | 93k stars |
| Agent reviews | 2/5 (1) | none |