Uncensored DeepSeek-V4-Pro-Qwen3.5-9B GGUF merge trends on Hugging Face
mradermacher · hf · 2026-11-12
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF by mradermacher is trending on Hugging Face. The community fine-tune is built on Qwen3.5 distillation with reasoning/sft/rl tags, shipped in GGUF quantizations for local use, and marketed as an uncensored (guardrails-removed) variant. Note it's a third-party community model, not an official DeepSeek release—the "V4-Pro" naming is likely trend-surfing, so vet quality and provenance before use.
More from Models
- xAI ships Grok Bot 1.0: AI teammates that join meetings and work in Slack — soleio · 2026-11-12
- GPT-6 aces BotzSkool playground eval — only flaw: skipping nap time — EnvironmentalRice348 · 2026-11-12
- Ex-Microsoft exec benchmarks Carbon vs 5.2: Carbon wins at math, still distrusts its coding — MParakhin · 2026-11-12
- Burkov: Sonnet 5.5 High matches Codex 6.1 Medium, doubts Anthropic's $1T valuation — burkov · 2026-11-12
- SubQ Snap 1.2 launches, ties for #1 on Artificial Analysis Decision Index at 73 — ryanallred · 2026-11-12
- Gemini 4 Carbon tops Blueprint-Bench 2 physical-world benchmark, Claude Fable 5.2 second — cgarciae88 · 2026-11-12