tech, developers, and the code underneath

issue 054· news·

Kimi K2 is a trillion-parameter open weights release

Moonshot ships a 1T-parameter MoE with 32B active, tuned for agentic tool use, with weights you can download.

Moonshot AI released Kimi K2: a mixture-of-experts model with roughly one trillion total parameters and 32 billion active per token, with open weights and a modified-MIT license.

A trillion-parameter open weights release is a milestone regardless of what you think of the benchmarks.

the architecture#

384 experts, 8 selected per token, 32B active. The design point is explicit: get the knowledge capacity of a very large model with the inference cost of a mid-sized one.

The training used MuonClip, a variant of the Muon optimizer with a QK-clipping mechanism to prevent attention logit explosion. The reported claim is zero loss spikes across the entire pretraining run on 15.5 trillion tokens.

If you have not run large pretraining: loss spikes are the recurring nightmare. A run destabilizes, you roll back to a checkpoint, you lose days of compute, and diagnosing why is largely folklore. A stability technique that actually works is worth more to the field than a benchmark point.

the agentic focus#

K2 was post-trained specifically for tool use, on synthetic multi-step tool-use trajectories generated at scale. The evaluation emphasis is agentic coding and tool-calling benchmarks rather than conversational quality.

That focus is the right read of where the demand is. The commercially interesting use of a model in 2025 is not answering questions, it is executing multi-step tasks with tools, and models tuned for chat are frequently worse at it than their raw capability suggests.

the practical problem#

You cannot run this on a workstation. A trillion parameters at 8-bit is a terabyte of weights. Even heavily quantized you are looking at multiple high-memory GPUs or a very large server.

So "open weights" here means something different than it does for a 30B model. It means:

  • Hosting providers can serve it, and several did within days, at prices well below frontier API rates.
  • Companies with infrastructure can run it privately, which is the point for regulated industries.
  • Researchers can study it, which is the underrated benefit. Interpretability work on frontier-scale models has been limited to whoever works at a frontier lab. It does not have to be.

the license#

Modified MIT with an attribution clause above certain usage thresholds. Not strictly OSI-compatible, much closer to open than most "open" model licenses, and substantially more permissive than the Llama community license.

The trend line here is good. Two years ago open weights meant a research-only license with a list of prohibited uses. Now the frontier of open releases is MIT and Apache 2.0 with narrow carve-outs.

the pattern nobody should miss#

The most permissively licensed, largest, most capable open weights models are overwhelmingly coming from Chinese labs — DeepSeek, Qwen, Moonshot, Zhipu, MiniMax. Western open weights releases have been smaller and more restrictively licensed.

The strategic logic is not complicated: if you are behind on distribution, you compete on openness. It worked for Meta in 2023 and it is working now.

The practical consequence for a developer is that your best option for a private, self-hosted, high-capability model is increasingly a Chinese release. Evaluate it on your own tasks, run it in your own infrastructure, and make the decision on engineering grounds.

get README in your inbox

One dispatch, no noise. Tech and developer news, plus the occasional long piece on the craft.

subscribe →