deepseek-ai/DeepSeek-V4-Flash-DSpark
deepseek-v4-flash-dspark
165Bmitcatalogued β€” not yet read
Provenance & integrity
Revisionnot enriched
Parameters165BΒ· 165,265,000,000 params
Licencemit
Released2026-06
Makerdeepseek-ai
Last modifiednot enriched
Accessopen access

This model is catalogued from public listings; no artifact fingerprint has been captured β€” provenance shows identity only, not the integrity of a specific file.

The reading
β—‹ Cataloguednot yet read β€” no reading has been published for this model. Identity and provenance stand on their own; disposition is left blank rather than guessed.
Claim grounding
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence Technical Report πŸ‘οΈ Note: DeepSeek-V4-Flash-DSpark is not a new model. It is the same checkpoint with an additional speculative decoding module attached. A minimal inference example is available in the inference folder. For more details, refer to: https://github.com/deepseek-ai/DeepSpec Introduction We present a preview version of DeepSeek-V4 …
β€” the uploader's card, captured 2026-07-08, quoted verbatim Β· source β†—