Beberapa demo cepat Qwen 3.8 sejak waktu kita dengan 3.8 hampir berakhir.

Strata IQ3_S - Qwen 3.8 Flash Next and Qwen 3.8 Flash Next FP8 official Ran both locally, ran my little colosseum prompt through both using Deepseek harness, pretty good results on both.

Loktar 🇺🇸Nov 1048

Bagaimana jika agen AI berhenti melakukan semua pekerjaan dan mulai mengelolanya?

👀 Fable 5.2 was tested with 3 local Qwen 3.8 27B agents handling the actual building. The results: ⚡ 21 min → 11 min 💰 $15.77 → $2.98 🤖 2,860 lines of code written by Qwen 🧠 Fable focused on

Kimi | Crypto & AINov 106

Selamat datang di kolam kecil pokemon commonstack_ai saya

Qwen 3.8 flash is quite elite

Hexx ./Nov 1020

Qwen 3.8 27B di Mac Studio saya adalah satu-satunya model yang benar-benar membuat gletser, aurora

Same prompt on three stacks. GLM 5.3 Flash on the 4 box Spark ring hit 180 tok/s and DeepSeek V4.1 Flash hit 150. Speed isn't everything.

CryptoBanditNov 101