LightSeek Foundation released a Kimi K3 draft-model collection (EAGLE-3, DFlash2, DSpark) trained with TorchSpec on 40 NVIDIA GB200 GPUs, with open data recipes. Their blog reports acceptance length across 10 benchmarks and SPEED-Bench end-to-end throughput; DFlash2 averages ~4.02 accepted tokens and leads EAGLE-3 at lower concurrency.

Key Takeaways

  • ✓Three draft architectures for Kimi K3 speculative decoding: EAGLE-3, DFlash2, DSpark.
  • ✓Trained on 40×GB200 with TorchSpec; data recipes plus Docker/CI shared.
  • ✓On HumanEval, DFlash2 acceptance length ~5.08 vs EAGLE-3 ~3.29.
⚡

Key Decision Metrics at a Glance

TL;DR Verdict
🏆 Benchmark RankRank
No model benchmark in this story · see current rankings
Full Leaderboard→
💰 Cost & PlansCompare
API & Subscription
Compare Plans↗
🛠️ Ecosystem & IDERules
Kimi K3 · LightSeek · TorchSpec
Setup IDE Rules↗
🧭

Not enough VRAM? Compare cloud API and self-hosting costs

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

⚔️ Compare Model→💰 Cloud cost calculator↗
Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

⚔️ Launch VS Compare→💳 View Plans↗
Up NextvLLM and NVIDIA ship a specialized Kimi K3 decode path on GB300: 842 tok/s at batch 1, 1.3–1.9x faster without speculation
Read Now→