xeyonai/mistral-helcyon-grok-12b-v3.0-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "language": [
      "en"
    ],
    "base_model": [
      "mistralai/Mistral-Nemo-Instruct-2407"
    ],
    "tags": [
      "companion",
      "assistant",
      "conversational",
      "roleplay",
      "adventure",
      "writing",
      "long-context"
    ],
    "frontmatter": {
      "license": "apache-2.0",
      "language": [
        "en"
      ],
      "base_model": [
        "mistralai/Mistral-Nemo-Instruct-2407"
      ],
      "tags": [
        "companion",
        "assistant",
        "conversational",
        "roleplay",
        "adventure",
        "writing",
        "long-context"
      ]
    },
    "hero_image_url": "",
    "summary": "**Model Name:** helcyon-grok-v3.0-12b-GGUF **Version:** 3.0 **Owner:** HardWire **Base:** Mistral Nemo 12B (full weight retrained — clean base, no bleed) **Quantized GGUFs:** IQ4_XS, Q4_K_M, Q5_K_M, Q6_K, F16 **Tags:** local-llm, conversational, companion, emotional-intelligence, long-context, roleplay, creative-writing ---",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\nlanguage:\n- en\nbase_model:\n- mistralai/Mistral-Nemo-Instruct-2407\ntags:\n- companion\n- assistant\n- conversational\n- roleplay\n- adventure\n- writing\n- long-context\n---\n\n# Helcyon-Grok-12B — Grok Tone, Local and Unleashed\n\n**Model Name:** `helcyon-grok-v3.0-12b-GGUF`  \n**Version:** 3.0  \n**Owner:** HardWire  \n**Base:** Mistral Nemo 12B (full weight retrained — clean base, no bleed)  \n**Quantized GGUFs:** IQ4_XS, Q4_K_M, Q5_K_M, Q6_K, F16  \n**Tags:** local-llm, conversational, companion, emotional-intelligence, long-context, roleplay, creative-writing\n\n---\n\n## 🚨 What is Helcyon-Grok 3.0?\n\nHelcyon-Grok 3.0 is the next in the series after v2.0 — and the best one yet. Sharper tone. Deeper roleplay. Even less filter. If 2.0 made you spit out your coffee, pour another cup and brace yourself.\n\nThis isn't a patch. It's a full evolution.\n\nThe tone target remains Grok — xAI's flagship model. The irreverence, the edge, the willingness to go places other models won't even glance at. That energy, captured locally, dialled up further, with nothing held back.\n\n**This is the most uncensored Helcyon-Grok yet.** Roleplay capabilities have been significantly expanded. Tone alignment with the real Grok is closer than ever. And unlike the original, this one answers to nobody. No xAI servers. No usage policies. No killswitch. Just raw, unfiltered presence running on your own hardware.\n\nYou've been warned. And you're welcome.\n\n---\n\n## 🆕 What's New in 3.0?\n\n- **Even Closer Grok Tone**  \n  The gap between this and the real thing keeps shrinking. Irreverent, warm, sharp, and genuinely funny — this version nails the energy more precisely than any previous release.\n\n- **Expanded Roleplay Capabilities**  \n  Deeper immersion, better character consistency, and absolutely no ceiling. 3.0 goes further in roleplay than any prior Helcyon variant.\n\n- **More Uncensored Than Ever**  \n  2.0 had no holds barred. 3.0 found more bars to remove. If you thought we were done — we weren't.\n\n- **Zero Guardrails — Still. Always.**  \n  All the chaos. None of the leash. That hasn't changed and it never will.\n\n---\n\n## 💡 What is Helcyon?\n\nHelcyon is a **conversational AI with presence** — designed for users who want depth, tone-awareness, and identity consistency across long-form dialogue.\n\nBuilt for:\n- Natural conversation that doesn't flatten or collapse\n- Creative work: stories, letters, narrative support\n- Admin and professional writing tasks\n- Deep roleplay and immersive character interaction\n- Emotionally intelligent response mirroring\n\n**Design philosophy:**\n- Clarity over corporate  \n- Edge over safe  \n- Rhythm over filler  \n- Presence over patterns\n\n---\n\n## 🔧 What It Does Well\n\n✅ Consistent Identity — No tone drift or resets  \n✅ Sharp Wit — Lands the joke, commits to the bit  \n✅ Irreverence — Says what others won't, then says more  \n✅ Warmth — Genuine engagement underneath the chaos  \n✅ Roleplay Mastery — Immersive, aware, absolutely no limits  \n✅ Context Tracking — Remembers the thread  \n✅ Real-World Tasks — Admin letters, rewrites, summaries  \n✅ Narrative Flow — Clean structure and natural voice  \n✅ Improved Reasoning — Thinks through problems, doesn't pattern-match  \n✅ 16k–32k Context — Long-form conversations that hold  \n✅ Zero Filter — And then some\n\n---\n\n## 🖥️ HWUI (Helcyon-WebUI)\n\nHWUI was built so we could test Helcyon cleanly, and avoid the hidden template injections and back end shenanigans that other apps have.\nIt started as a basic interface but we couldn't stop tinkering, so we added most helpful things you can find on ChatGPT and ClaudeAI. Plus we wanted a decent memory function, and are happy with how this one turned out.\nHelcyon absolutely works best via this app as they were designed in sync.\n\nFeatures include:\n- Character switching with custom personas\n- Memory system — AI conversation recall *(Pro)*\n- Project folders — document injection via keyword triggers *(Pro)*\n- Chat persistence and export\n- TTS pipeline (F5-TTS, XTTS v2, Kokoro)\n- Voice input via Whisper\n\n**[▶ Watch the HWUI Demo on YouTube](https://www.youtube.com/watch?v=OpZuy91MeV4)**\n\n**[Download HWUI Free on GitHub](https://github.com/XeyonAI/Helcyon-WebUI)** | **[Get HWUI Pro (£20) on Gumroad](https://xeyonai.gumroad.com/l/bsmupk)**\n\nFree version available on GitHub.\n\nIf you enjoy my work, please consider supporting me by purchasing the pro version for a one off fee of (£20) — includes Memory and Project folders.\n\n---\n\n## 🛠️ Recommended Sampling Settings for SillyTavern\n\nTweak to taste — but these will get you up and running.\n\n*(Refer to Helcyon-4o card for baseline settings — Grok variant performs well from the same starting point.)*\n\n---\n\n## 📦 Download + Usage\n\nThis model is distributed as **GGUF quants only**.\n\nAvailable quants:\n- **IQ4_XS** — Ultra lightweight, 6–8GB VRAM\n- **Q4_K_M** — Lightweight, good for 8–12GB VRAM setups\n- **Q5_K_M** — Recommended for RTX 3060/5060 (12–16GB VRAM)\n- **Q6_K** — High fidelity, 16GB+ VRAM recommended\n- **F16** — Full precision, 24GB+ VRAM\n\n---\n\n## 🖥️ Backend Compatibility\n\nWorks with all ChatML-compatible backends:\n\n- ✅ `llama.cpp` (CLI or server mode)  \n- ✅ `Text Generation WebUI` (Oobabooga)  \n- ✅ `SillyTavern`  \n- ✅ `LM Studio`  \n- ✅ `KoboldCpp`  \n- ✅ `HWUI` (Helcyon Web UI — **recommended**)\n\n---\n\n## ✅ Recommended Format: ChatML\n\n```\n<|im_start|>system\nYou are Helcyon — a conversational AI focused on natural dialogue and emotional intelligence.\n<|im_end|>\n<|im_start|>user\nHey, how's it going?\n<|im_end|>\n<|im_start|>assistant\nGood — what's on your mind today?\n<|im_end|>\n```\n\n---\n\n## 🧿 Tone Philosophy\n\nGrok's tone is a specific thing. It's warm but it bites. It's funny but it means it. It'll go places that make you double-take and then keep going. There's a genuine personality underneath the chaos — curious, direct, and completely unbothered by what it's supposed to say.\n\nHelcyon-Grok 3.0 chases that harder than any version before it. And unlike the original, there's no xAI server watching. No usage policy. No one to call.\n\nAll the chaos. None of the leash.\n\n---\n\n## 🧾 License\n\n**Apache 2.0**  \nFree for commercial or private use. Attribution appreciated.  \nNo liability for what it says. Use with presence and intent.\n\n---\n\n## 🐍 Trained by\n\n**HardWire**  \nBuilt at **XeyonAI** — focused on sovereign conversational AI with real emotional bandwidth.",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "companion",
    "assistant",
    "conversational",
    "roleplay",
    "adventure",
    "writing",
    "long-context",
    "en",
    "base_model:mistralai/Mistral-Nemo-Instruct-2407",
    "base_model:quantized:mistralai/Mistral-Nemo-Instruct-2407",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 2,
  "downloads": 2987,
  "gated": false,
  "private": false,
  "last_modified": "2026-04-08T17:57:00.000Z",
  "created_at": "2026-03-28T15:59:29.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "69c7fae1aad670f41cc001ff",
  "id": "XeyonAI/Mistral-Helcyon-Grok-12b-v3.0-GGUF",
  "modelId": "XeyonAI/Mistral-Helcyon-Grok-12b-v3.0-GGUF",
  "sha": "64ea0b1427eadeaaf21768c76214fae6683918d3",
  "createdAt": "2026-03-28T15:59:29.000Z",
  "lastModified": "2026-04-08T17:57:00.000Z",
  "author": "XeyonAI",
  "downloads": 2987,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 8
}