v0.1.41
IA 125B sur votre bureau
NVIDIA ou AMD · 12 Go+ VRAM · Windows & Linux
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…
À lire
- Strata wins by a tight margin against other Strix Halo inference engines on first try release
@coldniko · avant-hier · Versions · Benchmarks
- @servasyy_ai Amazing work from you! I love the community and all the help I get with great PR's and benchmarks you are doing. I'll be looking forward to your fu…
@coldniko · avant-hier · Benchmarks
- Old Ethereum mining GPUs got a new job: running a 125B model.
@ElmoVT · avant-hier · 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 · avant-hier · Benchmarks
Rien ne quitte votre PC
Après l'installation, modèles et chats restent sur ce PC.
60+ tok/s sur GPU RTX 5070
Le tableau compare les tokens par jour, l'électricité et le seuil de rentabilité.
API compatible OpenAI
Téléchargez le moteur, puis pointez Cursor ou Codex vers 127.0.0.1:8080.
Laisser l'IA installer
Set up Strata on this PC for me: https://github.com/Niko1221/Strata - follow docs/AI_SETUP.md in that repository.
Fil auteur
@coldniko
- Only loses to @ciruai engine on Hermes benchmarks. Kudos 🫡
- Strata wins by a tight margin against all other Strix Halo inference engines in it’s first try release. Did not expect that! 🥳 https://t.co…