You can now run Qwen3.8 Flash Next locally on an 8GB GPU at 20+ tokens/sec.
This is a dev post classified by AGK Intelligence as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
You can now run Qwen3.8 Flash Next locally on an 8GB GPU at 20+ tokens/sec. - Massive parallelism gains across the board. - Dual NVIDIA cards up to +98% faster. - Strata 0.2.10 just dropped with huge multi-GPU and long-context improvements. - https://github.com/Niko1221/Strata/releases/tag/v0.2.10
Posted by Md Ismail Šojal 🕷️ (64.6k followers) 1 h ago · 3 likes · 1.5k views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: strata, deepseek-v4.1-flash-1017-gguf.
More dev work like this
- Post novo: "Criando um framework para IA com IA: REA Launcher SDK" — @AkitaOnRails
- Test AI trading agents without putting real money on the line. — @DanKornas
- 🚨Pulse Alpha is almost certainly a new model from Thinking Machines, and it's already… — @SPAC89
- Claude wrote entire working transformers by hand. — @0x0SojalSec
- I told GPT-6.1 Sol to make a small model more Shakespearean, and it did it — @AdamHoltererer
- Too good of a result to not share, DeepSeek-v4.1-Flash-1017 ofcourse ! — @ItsmeAjayKV
- Grok Build v1.0.74 is out with a few practical updates. Standouts include messages… — @blankspeaker
- Today, @llama_index is an applied research lab building models and agents for document… — @jerryjliu0
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.4k posts from 5k X accounts over the last 21 days, 9.1k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-03 01:46 UTC. Full method.