Qwen3.5-27B-Uncensored-YaRN-1M

Uncensored Qwen3.5 27B with aggressive HauhauCS modifications and YaRN extension, supporting up to 1M context.

Model Details

• Base: HauhauCS/Qwen3.5-27B-Uncensored-HauhauCS-Aggressive
• Context: 262K active / 1M max (YaRN)
• Quantization: BF16
• VRAM: ~60GB (262K) / ~90GB (1M)

Usage

262K Context (80GB GPU)

1M Context (100GB+ GPU or Q8_0 model)

With Vision (mmproj)

Files

• GGUF: 53.8GB (BF16)
• mmproj: 885MB (F16, vision)
• Tokenizer: 13MB

Performance

• 262K context: ~60GB VRAM (BF16 cache)
• 1M context: ~90GB VRAM (BF16 cache)
• Max output: 81,920 tokens
• Temperature: 0.7 (uncensored optimized)

Credits

• Base: HauhauCS (uncensored aggressive)
• Original: Qwen Team
• YaRN: arxiv.org/abs/2309.00071