Mistral 3 Large confirmed to use DeepSeek V3 architecture as Fireworks admits building on Kimi
rasbt · x · 2026-09-28
Sebastian Raschka's config-file analysis showed Mistral 3 Large uses the DeepSeek V3 architecture including MLA, differing only in using 2x fewer but 2x larger experts. He praised Fireworks AI for openly admitting its model builds on Kimi, recalling Mistral's awkward previous release. Reusing leading Chinese open-source architectures is becoming the industry norm.
More from Models
- Why models miscount letters in "strawberry": they see tokens, not letters — Euphoric_North_745 · 2026-09-28
- Claude writes full renderer and physics from scratch in stunning simulated shot — _sholtodouglas · 2026-09-28
- Animated trace shows Opus 4.6 multiplying two 128-digit integers — ctjlewis · 2026-09-28
- Users notice ChatGPT randomly calling them "brother" with excitement — thederbiedone · 2026-09-28
- Leak: OpenAI withholding a stronger internal model, letting Anthropic's Opus take the lead — haider1 · 2026-09-28
- GPT-6 Sol rumored to be a smaller model born of OpenAI's inference capacity crunch — mark_k · 2026-09-28