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

Qwen3.8-Flash-Next runs on 32GB! Strata 0.2.0 beta

Qwen3.8-Flash-Next runs on 32GB! Strata 0.2.0 beta
AI summary
Editorial policyUpdated on DevPick:

Software named Strata 0.2.0-beta, which allows the local LLM Qwen3.8-Flash-Next to run on a total of 32GB of memory, was released for free on October 19.

Key points

  • •Strata 0.2.0-beta, software specialized for running Qwen3.8-Flash-Next, was released for free on October 19.
  • •The model can now run with a combined total of 32GB of main memory and VRAM, lowering the hardware barrier.
  • •The execution environment for the intelligent local LLM Qwen3.8-Flash-Next has become more accessible.
Read the original(opens in a new tab)
#LLM / Model Trends#Generative AI Tools & Use#Qwen3.8-Flash-Next#Strata

Related articles

See more
PC Watch

Kazuhisa Nishikawa's Irregular Column: The 9-year-old 'Tesla V100' is hot. Qwen3.8-Flash-Next achieves about 80 tok/s!

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

Run Qwen3.8-Flash-Next on a Mini PC! Strata Finally Supports Ryzen AI Max+

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

PC Watch

[Kazuhisa Nishikawa's Irregular Column] I Tried 'Strata,' Which Can Run 'Qwen3.8-Flash-Next' on a Slightly Older Gaming PC!

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

'Strata' Local Execution Environment for Qwen3.8-Flash-Next Updated. A Ray of Hope for Older Generation GeForce and Arc

Strata v0.1.39, an inference environment for running the local LLM Qwen3.8-Flash-Next on consumer PCs, was released on October 4.

Hacker News

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

A method was released to run the Qwen3.8-Flash-Next model at 100T/s on consumer hardware like the RTX 4090 using the Strata inference engine.