Qwen 3.8 Next Flash 4bit MTP di M3U Studio saya benar-benar berfungsi sekarang.

Proses OMP terbaru saya mengukur decode keseluruhan 97,1 tok/s pada konteks 23k, dengan ~1.131 tok/s PP yang tidak di-cache. PR dibuka di oMLX untuk ini.

Ash HartSep 1377

Holy smokes qwen-3.8-27b on cerebras with Hermes Agent feels so good and fast it's almost unreal.

Testing with the upcoming Cadu app by fl_rn_st. Tool calls are now the main slowdown 😅

Federico ViticciSep 13143

DeepSeek V4.1 Flash is now listed with free access on Apinex—and the catalog includes several other models

DeepSeek V4 Pro • DeepSeek V4 Flash • Gemini 3.8 Flash • GLM 5.3 Flash • Muse Spark 1.3 • GPT-5.6 Luna • Qwen 3.8 Max Browse the models:

Tung AirSep 13

Operating System powered by Qwen 3.8 27B at 1950 tokens/sec!

Here is what 1,950 tokens/second Alibaba_Qwen's 3.8 27b actually looks like on cerebras: i wrote a minimal python web server that turns cerebras inference into a live operating system. zero apps on disk. when you

AlokSep 13221