tiba-tiba kimi di opencode? ㅋㅋㅋ
di open-webui memang mereka berbicara tentang qwen...
{"object":"list","data":[{"id":"qwen3.8-27b","object":"model","created":1787119523,"owned_by":"vllm","root":"Qwen/Qwen3.8-27B","parent":null,"max_model_len":524288,"permission":[{"id":"modelperm-8f041d7ea3598863","object":"model_permission","created":1787119523,"allow_create_engine":false,"allow_sampling":true,"allow_logprobs":true,"allow_search_indices":false,"allow_view":true,"allow_fine_tuning":false,"organization":"*","group":null,"is_blocking":false}]}]}
Sedang menjalankan model asli tanpa kuantisasi di RTX PRO 6000
Kecepatan generasi token tidak secepat yang dipikirkan. avg gen throughput sekitar 30 token.
Saya akan mencoba menerapkan MTP.
