DeepSeek new-model rumor retracted: fingerprint matches old model
teortaxesTex · x · 2026-10-15
A self-correction to the DeepSeek new-model rumor: the model fingerprint (aeb56401ca74e127821c4f9126dcb669) matches the old model, and speed is 240 t/s excluding ttft. The poster admits it was 'false alarm… I was high on hopium.' The substance of this event is covered in the companion post.
Related event: DeepSeek V4.1 Rumor Debunked After Fingerprint Check(2 posts)→
More from Models
- Step 5 Preview architecture blog details Sparse GQA with block-wise token merging cutting indexer cost 8x — teortaxesTex · 2026-10-15
- Fish Audio Drama 3 lands in vLLM-Omni: 128 concurrent streams on one H200 — vllm_project · 2026-10-15
- Why is GPT-6 Astra ranked so low on LM Arena? Outscored by GPT-5.6 and 6.1 — AreaExact7824 · 2026-10-15
- Stance test heat map shows Sonnet 5.5 resists framing manipulation other models succumb to — teortaxesTex · 2026-10-15
- Argon (Medium) burned 85% of a 5-hour usage limit in just 5 minutes — Avalunne · 2026-10-15
- Score vs cost chart puts Gemini 4 Argon on the Pareto frontier, Kimi K3 far off it — Hesamation · 2026-10-15