Entries for June 20, 2026

I created an LLM leaderboard based on Hugging Face download and like counts, grouped, filtered and time-averaged. Top 5 downloads is shared by @Alibaba_Qwen and @googlegemma 👑🤝👑 Top 5 likes, on the other hand also includes @deepseek_ai V4 Pro 👑 Even @OpenAI makes it to #8 top downloads with gpt-oss-20b 👑 qwen3-6-35b-a3b is the second most CIRCULATED LLM of this year, with an average of 21 million downloads per month, since the day it was released 2 months ago 📈📈📈 Despite first place belonging to 8mo old qwen3-vl-2b-instruct, the highlight belongs to the mid-sized MoE model, which has hit a size/performance sweet spot so hard that it absolutely 💥 SHATTERED 💥 Hugging Face leaderboards in the 2 months since it has launched qwen3-6-35b-a3b is followed closely by its dense sibling 27b --- and then the mid-sized gemma 4 models 26b-a4b and 31b Note that a model's distribution is inversely proportional to its size, but not strictly! Usefulness plays a factor as well, since gemma 4 26b-a4b is being downloaded more than the smaller gemma 4 e4b I created this leaderboard because Hugging Face's all time highest downloads and likes did not give me enough information about what is really popular, neither today, nor all-time. I wanted something in between How do I calculate this ranking? - Get models that with n_downloads >= 100k - Exclude models older than 1 year - Deduplicate and group quantizations and variants of the same model based on slug prefix heuristics - For each group, sum up total downloads of all time - Sort by descending total_downloads / age = average_downloads_per_day (can also sort w.r. to likes per month) - Repeat every day to get the most up to date ranking More info and source on the leaderboard page, hosted on a Hugging Face space: osolmaz-leaderboard.hf.space This is a work in progress, please reply below if you see a model that should be there is missing, or any other mistakes

I just deleted an earlier post about ranking of HF models based on their total downloads because I made an error Will post with updated values soon

gemma-4-26b-a4b is the most CIRCULATED LLM of recent history, with an average of 126k downloads per day, since the day it was released 3 months ago Top 10 is shared by Qwen and Gemma, with DeepSeek V4 Pro coming in close 🤝 Note that a model's distribution is inversely proportional to its size, but not strictly! Usefulness plays a factor as well, since gemma 4 26b-a4b is being downloaded more than the smaller gemma 4 e4b I created this leaderboard because Hugging Face's all time highest downloads and likes did not give me enough information about what is really popular *these last few months* How do I calculate this ranking? - Get models that with n_downloads >= 100k - Exclude models older than 1 year - Sort by descending total_downloads / age = average_downloads_per_day (can also sort w.r. to likes per month) - Deduplicate quantizations etc. of the same model based on slug prefix heuristics More info and source on the leaderboard page, hosted on a Hugging Face space: osolmaz-leaderboard.hf.space

I need better UI/UX on queueing messages to agents. I want to be able to: switch the order of queued messages pause the queue edit any message that are still in the queue undo steer messages in the few seconds they are being sent I want more visual emphasis on the queue, like a Queue View I can toggle, that puts the queue at the center I want this in all the UIs and coding agents, codex CLI, desktop, moshi... especially while on the phone

saving the world from AI cartelization for fun and profit