Compare repositories
This page shows the Star History and the facts of 2 to 5 repositories in the Repository Index, side by side. You choose the repositories. The page does not rank them.
Facts
| Fact | Anbeeld/beellama.cpp KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM | JakeATX/llamAmpere llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s over a 100K-token generation at temperature 1 for qwen3.8, supporting full 262K ctx. Supports low memory (12gb) configs for 200k+ ctx. 120+ TPS, 3300+ prefill for QFN 3.8. |
|---|---|---|
| Stars | 1,197 | 387 |
| Net stars, last 30 days | +45 | +209 |
| Largest star day | +99 on May 16, 2026 | +43 on Nov 11, 2026 |
| Milestone reached in the record | 1,000 on Sep 2, 2026 | 100 on Sep 20, 2026 |
| Forks | 82 | 45 |
| Language | C++ | C++ |
| License | MIT | MIT |
| Created | May 5, 2026 | Sep 7, 2026 |
| Last push | Nov 17, 2026 | Nov 14, 2026 |
| Archived | No | No |
| Health facts: Maintenance | 2 of 4 checks (2 without data) | 4 of 4 checks |
| Health facts: Releases | 1 of 3 checks (1 without data) | 2 of 3 checks |
| Health facts: Security practice | 0 of 1 check (1 without data) | 1 of 1 check |
| Health facts: Community files | 1 of 3 checks (2 without data) | 2 of 3 checks |
| Commits, last 13 weeks | No data | 2,815 |
| Weeks with commits, last 52 | No data | 52 of 52 |
| In the Repository Index since | Nov 14, 2026 | Nov 12, 2026 |
Topics that all of them have on the Repository Host: ggml, llama-cpp, llm-inference, quantization, llm. The facts come from the Repository Host and from the Star History that AwesomeRepos records. A shared topic does not mean that one repository can replace another. Each Health Facts row is one dimension alone. AwesomeRepos does not add them into one score. How each check is defined