Kronos is a self-evolving training pipeline targeting Opus-4.6-parity
on coding benchmarks at $1/M output tokens,
2M context, 150–200 tok/s.
All scripts, datasets, and intermediate checkpoints are public.
€100
seed capital
€0
spent so far
Qwen2.5-Coder-1.5B
Round-0 base model
LCB-Lite
evaluation benchmark
Status
Round-0 training currently live on Kaggle P100. LoRA on Qwen2.5-Coder-1.5B + 5K CodeFeedback rows.
Round-1A (7B), Round-2 (distill), Round-3 (GRPO RL) plans pre-pinned. See vault/experiments in scripts dataset.
Cheap-first ladder: Kaggle/Colab free GPUs → grant credits → small paid GPU bursts → revenue-funded scale.
Distillation Round 2: Qwen3-Coder-480B teacher fixes ~50% of student failures on LCB-medium (empirically validated cycle 38–39).
RL Round 3: GRPO + binary code-execution reward on the residual systemic failures distillation can't fix.
Speculative decoding Round 6: DFlash block-diffusion drafts for 2–3× throughput at serve time.
Early access
Want to try the model when Round-3 lands? Drop your email.
Paid early-access tier (€10–20/mo with usage cap) opens after the first Opus-4.6-comparable checkpoint.