v0.1.41

IA 125B en tu escritorio

NVIDIA o AMD · 12 GB+ VRAM · Windows y Linux

Instalación en un clic Novedades v0.1.41 Comunidad · Issues y PR Benchmarks de hardware GitHub

v0.1.41

Strata v0.1.41

Faster on more than one GPU, faster short prompts on NVIDIA, about twice as fast prompts on Windows with little RAM, and a long list of fixes. Two defaults change: --batch on a layer split now runs one pipeline group per GPU, and short prompt chunks on one NVIDIA GPU get help fro…

Versiones Descargar Benchmarks Pulse · 24

Para leer

Old Ethereum mining GPUs got a new job: running a 125B model.
@ElmoVT · anteayer · Benchmarks
125B params at 94 tok/s on a 12GB RTX 5070. Strata runs Qwen 3.8 Flash Next on a gaming PC with 64GB RAM, Q2 quant. a year ago this needed a rack. https://t.co/…
@arnabkarmkr · anteayer · Benchmarks
Time for test results of Qwen3.8-flash-next-GSQ-RSO-IQ3_S on my 3090
@ItsmeAjayKV · anteayer · Benchmarks
Forget the top-tier 5090. The PNY RTX 5080 Slim is on an incredible deal, offering massive value. Even better, the RTX 5070 Ti delivers nearly the same performa…
@thetechnotice · anteayer · Benchmarks

Pulse

Nada sale de tu PC

Tras instalar, los modelos y los chats se quedan en este PC.

60+ tok/s en GPUs RTX 5070

En la tabla: tokens al día, electricidad y punto de equilibrio.

API compatible con OpenAI

Descarga el motor y apunta Cursor o Codex a 127.0.0.1:8080.

Deja que la IA instale

Set up Strata on this PC for me: https://github.com/Niko1221/Strata - follow docs/AI_SETUP.md in that repository.

Pulse autor

@coldniko

Ver todo