Expired50% confidenceBenchmarkExact time
On consumer GPUs with 12GB to 16GB of VRAM, Strata can achieve generation speeds of 40 to 95 Token/s when running a 125B MoE model.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/4/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 11/18/2026(expired)
Sources
Running 125B MoE on a 12GB GPU? Inside Strata's Three-Tier Cooperative Engine
bilibiliNicksxs11/3/2026
Related Entities
Related Claims
UnverifiedStrata is a local inference engine that can run 180B-class MoE models on consumer-grade GPUs with 12 GB of VRAM.79% similarUnverifiedStrata enables a single GPU with 12 GB of VRAM to smoothly run Qwen3.8 Flash Next, a large model with 125 billion activated parameters and an overall size of 176B.72% similarVerifiedIf bandwidth reached 2.4 TB/s, the theoretical speed ceiling for a 100 GB model could reach 24 tokens/s, a 60 GB model 40 tokens/s, and a 35 GB model close to 69 tokens/s.71% similarUnverifiedStrata can run with 12GB of VRAM plus 32GB of RAM.71% similarUnverifiedRunning Large 4 on a typical laptop with 16GB/32GB of memory generates at about 15 tokens per second.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1134853API
curl https://kongchang.com/api/v1/knowledge/claims/1134853MCP
get_claim(id=1134853)