Unverified50% confidenceFactExact time
On a single RX 7900 XTX 24G GPU, the Strata engine can fully run the approximately 125B-parameter Qwen3.8 Flash Next MoE model, supporting both text inference and image recognition.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
Partially VerifiedQwen3.8-Flash-Next adopts a Mixture of Experts (MoE) architecture with 125B total parameters and 6B activated parameters.76% similarUnverifiedAlibaba's Tongyi Qianwen officially released the Qwen3.8-Flash-Next (Qianwen 308 Flash NEX) model, with a total parameter count of 181.5B.74% similarUnverifiedQwen3.8-Flash-Next uses the Strata inference engine in conjunction with MTP (Multi-Token Prediction) acceleration technology.70% similarVerifiedQwen 3.8 Flash Next adopts a Mixture of Experts (MoE) architecture.70% similarUnverified2×RTX 3090 can run Qwen 3.8 Flash, but requires substantial system memory support.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978733API
curl https://kongchang.com/api/v1/knowledge/claims/978733MCP
get_claim(id=978733)