Leaked test code hints at DeepSeek V4 Mini with 1M-token context and a V4 Pro sibling
teortaxesTex · x · 2026-09-30
A leak from DeepSeek's Harness repo test code suggests a small model is coming:
- Model ID deepseek-v4-mini, display name DeepSeek-V4-Flash, with context hard-coded at 1,000,000 tokens
- The same list also shows deepseek-v4-pro described as "Preserved hidden detail"
- Frontend code already handles model switching and Apply/validation flows—less like a throwaway mock, more like a lighter desktop-facing model in the works
teortaxesTex notes a single-GPU, 1M-context, heavily post-trained model with agent teams, local-first skills, trained on Huawei Ascend and with the recipe published could be an "R1 moment #2". Unconfirmed leak.
More from Models
- Polymarket claims GPT-6 Astra cracked a 217-year-old Napoleonic military cipher — Polymarket · 2026-10-01
- As model releases pile up, auto-routing between models may become standard for consumers — AnneliesGamble · 2026-10-01
- "No more pacing": developer flags quiet end to AI usage throttling — vivekhaldar · 2026-10-01
- Google models ace benchmarks but feel mid in use — will Gemini 4 Argon differ? — VraserX · 2026-10-01
- Jev reranker cuts cost to 75% while lifting recruiting search matches by 30.64% — hardimanjames · 2026-10-01
- minchoi's monthly roundup: 10+ model releases in one month from GPT-6 to Grok 4.7 — minchoi · 2026-10-01