Qwen 3.8 27B membangun kota saya pada malam hari dengan kecepatan 65 tok/s.

Setiap jendela bertumpuk di asalnya. Prompt yang sama pada tiga tumpukan. DeepSeek V4.1 Flash pada 4 kotak Spark ring mencapai 120,74 tok/s. GLM 5.3 Flash pada TensorFold 0.6.0 TP4 mencapai 108,0 tok/s. Qwen 3.8 27B di Mac Studio saja mencapai 65.23

CryptoBanditNov 65

Man, would you be so kind to run the Burj Al Arab test again?

Reaaaaally would like to compare it to my Qwen 3.8 Flash result. This one was created with Unsloth's Q6_K_XL using the DeepSeek Harness.

JayPowell (🥅,🥅)Nov 61

We have live Model APIs at urunml.

Here's Qwen 3.8 27B running on uRun, plugged into OpenCode over industry-standard chat completions. Same requests your code already sends, open model underneath. Read more here:

Keegan McCallumNov 61

Model APIs are live on uRun.

In the demo, we plug Qwen 3.8 27B into OpenCode and chat with it over industry-standard chat completions. Working internally, rolling out worldwide. Our waitlist gets access first: More:

uRunNov 62