Back to articles
DevPickView feed
PC Watchby 劉 尭
Original published:

ミニPCでQwen3.8-Flash-Nextをブン回せ！Strataが待望のRyzen AI Max+対応

AI summary
Editorial policy

Local LLM inference engine Strata now supports Ryzen AI Max/Max+ series, enabling Qwen3.8-Flash-Next operation with 128GB of memory.

Key points

  • •Version 0.1.40 of the open-source local LLM inference engine Strata was released on October 6.
  • •Experimental support for AMD's Ryzen AI Max/Max+ series was added.
  • •The engine can now run Qwen3.8-Flash-Next by utilizing 128GB of memory.
#Generative AI Tools & Use#LLM / Model Trends#Strata#Qwen3.8-Flash-Next
Read the original(opens in a new tab)

Related articles

See more
PC Watch

【西川和久の不定期コラム】9年前の「Tesla V100」がアツい。Qwen3.8-Flash-Nextが約80tok/s出る！

The Strata engine allows the Qwen3.8-Flash-Next MoE model to run at approximately 80 tokens per second on a 9-year-old Tesla V100 GPU by utilizing a three-tier memory hierarchy.

PC Watch

【西川和久の不定期コラム】ちょい古ゲーミングPCで「Qwen3.8-Flash-Next」を動せる「Strata」を試してみた！

Report on trial results of the tool "Strata," which runs the 125B parameter "Qwen3.8-Flash-Next" model on a 12GB VRAM video card.

PC Watch

Qwen3.8-Flash-Nextローカル実行環境「Strata」更新。旧世代GeForceやArcに一筋の光

ローカルLLM「Qwen3.8-Flash-Next」をコンシューマ向けPCで実行できる推論環境「Strata」の最新版v0.1.39が10月4日に公開された

Hacker News

Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s

推論エンジンStrataにより、Qwen3.8-Flash-NextモデルをRTX 4090などの消費者向けハードウェア上で100T/sの速度で実行できる手法が公開された

PC Watch

Qwen3.8-Flash-NextがゲーミングPCで爆速に動く「Strata」登場

AlibabaのQwen3.8-Flash-NextをゲーミングPCで高速実行する推論エンジン「Strata」が公開され、秒間60～95トークンで動作