One researcher pretrains coding model Mirendil-Base in 3.5 months on under $10M of compute
shayan_ · x · 2026-10-22
Mirendil announces a milestone in "pretraining at scale without a pretraining team": Mirendil-Base, its first pretrained coding model, was built from scratch by a single researcher in 3.5 months with under $10M in compute, covering all research, experimentation and the final training run. The team says early results are promising as it scales to larger models, and plans to release the tools. Ex-pretraining engineer Harsh Meh called this level of leverage "incredible."
More from Models
- DeepSeek V4.1 Flash hits 1,521 tok/s on Fireworks Ultrafast, ships Tetris in 11 seconds — nicolechirps · 2026-10-22
- Ingot quantizes Qwen 27B to FP8 in one week, beating Alibaba's own quantization — const_reborn · 2026-10-22
- Updated code cross-entropy chart: Mirendil-Base edges out Kimi-K3, Beam and Muse — bigblueboo · 2026-10-22
- Is PPL on internal code still a good pretraining eval when code is AI-generated? — josh_wills · 2026-10-22
- Claude Projects is really a scoped orchestrator, not account-wide memory — RileyRalmuto · 2026-10-22
- AA-PersonalityBench: Gemini models rank most confident and least likely to admit uncertainty — ArtificialAnlys · 2026-10-22