Downloads · 30 days
22
23% of all-time downloads
nakanokazuha/Yume-Qwen3.5-4B-GGUF
Yume-Qwen3.5-4B-GGUF is a text generation model from nakanokazuha. Use it when you need the model to write or continue text. The card lists the license as other.
An informal Indonesian conversational model with a tsundere personality. The model leans more heavily toward the tsun side than the dere side.
Downloads · 30 days
22
23% of all-time downloads
All-time downloads
95
Public
Repo size
2.7 GB
Likes
1
Public
Click a slice to open those files.
.gguf2.7 GB · 100%
From the Hugging Face model README
An informal Indonesian conversational model with a tsundere personality.
The model leans more heavily toward the tsun side than the dere side.
It was trained on approximately 1,200 conversations consisting of 2–3 turns, covering everyday scenarios.
The model is designed as a general-purpose assistant that can be integrated with Hermes, OpenClaw, or other agent orchestration platforms.
This model is experimental. Additional moderation and guardrails are still recommended, especially for high-risk or sensitive scenarios involving:
The base model is also uncensored, so generated responses are not inherently filtered.
llama-cli \
-hf nakanokazuha/Yume-Qwen3.5-4B-GGUF:Q4_K_M \
-cnv \
-ngl 99
Use the contents of system_prompt.txt to reproduce the same behavior used during release evaluation.
Q4_K_Mllama.cppv1.2