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 | youssofal/MTPLX The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server. | syv-ai/HyperQwen Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks. |
|---|---|---|
| Stars | 2,701 | 2,693 |
| Net stars, last 30 days | +131 | +708 |
| Largest star day | +87 on May 16, 2026 | +128 on Aug 25, 2026 |
| Milestone reached in the record | 1,000 on Jul 13, 2026 | 1,000 on Sep 1, 2026 |
| Forks | 212 | 339 |
| Language | Python | Python |
| License | APACHE-2.0 | APACHE-2.0 |
| Created | May 2, 2026 | Aug 15, 2026 |
| Last push | Nov 7, 2026 | Nov 10, 2026 |
| Archived | No | No |
| Health facts: Maintenance | 2 of 4 checks (2 without data) | 3 of 4 checks |
| Health facts: Releases | 2 of 3 checks (1 without data) | 0 of 3 checks (1 without data) |
| Health facts: Security practice | 0 of 1 check (1 without data) | 0 of 1 check |
| Health facts: Community files | 1 of 3 checks (2 without data) | 1 of 3 checks |
| Commits, last 13 weeks | No data | 749 |
| Weeks with commits, last 52 | No data | 13 of 52 |
| In the Repository Index since | Nov 11, 2026 | Oct 23, 2026 |
Topics that all of them have on the Repository Host: qwen, speculative-decoding, llm-inference, local-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