Gemma SEA-LION v4 27B

Qwen SEA-LION v4 32B

AI Singapore’s Qwen-based multilingual model, adapted for Southeast Asian languages and cultural contexts. Supports text chat and tool calling with a 128K context window.

Gemma 3 27B IT

Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions.

Qwen 3.8 27B Uncensored Fast by Heabsy

Heabsy's NVFP4 build of Qwen3.8-27B by Alibaba Cloud, with refusal removal based on huihui-ai's Huihui-Qwen3.8-27B-abliterated. Quantized and calibrated by Heabsy, with unpublished weights under the Heabsy Model License. Supports text and image input, tools, and optional reasoning capped at 16,384 tokens within the output budget. This named build is separate from Qwen 3.8 27B Uncensored.

Gemma 4 12B Starry Ocean

Gemma 4 12B Starry Ocean is an open-weight merge for storytelling, roleplay, and creative writing. It supports image understanding, tool calling, optional reasoning, and a 131,072-token context window.

Gemma 4 Dark Thoughts V2 31B

Ateron's second Dark Thoughts merge combines Dark Scarlett V2, MeroMero V2, and Scotoma 2 for creative dialogue and extended character roleplay. This text-only Gemma 4 31B deployment supports a 65,536-token context window and up to 8,192 output tokens.

Gemma 4 Gutenberg 31B

nbeerbower's Gemma 4 31B finetune for literary fiction, character interiority, and controlled narrative pacing. Its text decoder was trained with ORPO on 14,816 Athanorlite-DPO preference pairs. This text-only deployment supports a 65,536-token context window and up to 8,192 output tokens.