EAGLE

Repository facts

Stars

2,555

Forks

297

Open issues and pull requests

102

Primary language

Python

License

Other license

Owner

SafeAILab · Organization

Created

Dec 7, 2023

Last push

Feb 20, 2026

Topics

• large-language-models
• llm-inference
• speculative-decoding

Rank #3,005 of 9,507 in AI on GitHub, by stars. Data from the GitHub API, fetched Oct 18, 2026; star counts change daily. Stars measure popularity, not quality or safety, and a listing is not an endorsement. How this list is made

Related projects

Projects that share this one’s GitHub topics.

• 1,979

  Rank 1,979: raullenchai/Rapid-MLX

  Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents.…

  3,996 starsPythonOther licenseLast push Oct 18, 2026

• 2,959

  Rank 2,959: 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 speculati…

  2,598 starsPythonApache-2.0Last push Oct 10, 2026

• 3,585

  Rank 3,585: 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/…

  2,054 starsPythonApache-2.0Last push Oct 18, 2026

• 5,991

  Rank 5,991: StayLameBro/backburner

  Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable

  1,033 starsPythonMITLast push Oct 13, 2026

• 7,596

  Rank 7,596: ARahim3/mlx-dspark

  Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gemma-4, Qwen3.8, Muse-Glimmer, Nemotron, LFM…

  719 starsPythonMITLast push Oct 5, 2026

• 7,888

  Rank 7,888: ARahim3/kaggle-tpu-lab

  Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~165 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Wor…

  679 starsPythonMITLast push Oct 6, 2026