sjin59

c43g-s600m2

README

License: apache-2.0

Runs on vLLM 0.19.0. In bf16 it needs 2× H100 80GB (TP2). For single-GPU inference use the GGUF build, which fits on one RTX 3090 24GB.

Default sampling is temperature 0.6 / top_p 0.95 / top_k 20 — not greedy decoding.

Licensed under Apache-2.0, following the base model Qwen3.5-27B.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Model Details

Model Provider

sjin59

Model Tree

Base

Qwen/Qwen3.5-27B

Fine-tuned

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality

Dedicated Endpoints