Activity, over time
Daily GitHub activity and social mentions.
Mentions
Daily posts linking to this repository
Attention
Daily stars & forks
Star accumulation
Cumulative stars
Pull requests
Daily opens & merges
Conversations
Daily issues & comments
Community
Daily accounts & reviews
Trending history
Daily top 10 · last 90 days · UTC
Mentions
Stars
Forks
Contributors
Latest stargazers
The last 10 distinct accounts we observed this year.
Most active participants
PR, issue, comment & review events in the past year.
Packages
Scan pending.
Live mentions badge
Show how many posts mention your project in the last 30 days.
Live mentions · last 30 days
Mentions
Engine only and chat mode, explained in the README: 0xBakeer/TandemLLM Release notes: github.com/0xBakeer/TandemLLM/blob/main/CHANGELOG…
I am using this one 👇 on @TandemLLM Engine 0xBakeer/TandemLLM t.co
Qwen3.8 flash next on a single dgx spark 🔥 55k prompt, 133 tok/s peak 🤯 using TandemLLM Get it for free here 0xBakeer/TandemLLM t.co
six models, same 8 requests, one dgx spark every model card in @TandemLLM 0.15.0 github.com/0xBakeer/TandemLLM/releases/tag/v0.15.0 now has the same speed row, so i finally have one test for all of them. same prompts, 512 tokens each, temperature 1.0, thinking off, 3 rounds. total tok/s counted from the send, first tokens included. speed, one request: lfm2.5-24b-a2b 122.8 flint 108.3 flash-next 44.1 qwen3.8-27b 35.3 bolt 35.2 ornith-1.5-122b 34.5 speed, 8 at once: lfm2.5-24b-a2b 238.6 flint 215.9 qwen3.8-27b 146.3 flash-next 108.2 bolt 92.2 ornith-1.5-122b 85.5 surprise: the 27b grows 4.1x from 1 to 8 requests. every other model stays between 1.9x and 2.6x. one of the slowest alone ends up third. thanks @liquidai, nvidia, qwen and @ornith_ for the models and turboderp for the flash-next pack 🙏
Very fast model to run on one dgx spark for daily chats up to 300 tok/s on 0xBakeer/TandemLLM