GitHub repo leaderboard by stars, growth rate and activity.

• BlinkDL

  #1BlinkDL/RWKV-LM

  RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

  Python14,701 starslast pushed 1 week ago
• FareedKhan-dev

  #2FareedKhan-dev/kimi-k3-in-c

  A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

  C7,537 starslast pushed 19 hours ago

#	Repo	Language	Stars	30-day trend	Last updated
1	BlinkDL BlinkDL/RWKV-LM RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.	Python	14,701		last pushed 1 week ago
2	FareedKhan-dev FareedKhan-dev/kimi-k3-in-c A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.	C	7,537		last pushed 19 hours ago

All · 11,658