Expired50% confidenceFactExact time
DeepSeek officially provides multiple distilled versions based on the Qwen and Llama architectures, with parameter counts ranging from 1.5B to 70B.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/25/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/23/2026(expired)
Sources
Redis之父如何将2840亿参数DeepSeek塞进普通笔记本
Related Claims
Unverified千问（Qwen）和DeepSeek都提供了基于MOE架构的版本79% similarUnverifiedOpen-source large model families such as Qwen, Mixtral, and DeepSeek all adopt MoE designs.74% similarUnverifiedDeepSeek V4 comprehensively leads Qwen 3.5, Kimi K2.6, Gemma 5.1, and other open-source models across all metrics.73% similarPartially VerifiedDeepSeek R1 offers multiple distilled versions ranging from 1.5B to 671B parameters.73% similarUnverifiedDeepSeek has multiple distilled versions, including 7B, 14B, and 32B specifications, which compress the reasoning capabilities of large models into smaller models through knowledge distillation technology.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/613503API
curl https://kongchang.com/api/v1/knowledge/claims/613503MCP
get_claim(id=613503)