xeyonai/mistral-helcyon-grok-12b-v2.0-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-v2.0-12b-GGUF **Version:** 2.0 **Owner:** HardWire **Base:** Mistral Nemo 12B (full weight retrained — new base, no Mercury bleed) **Quantized GGUFs:** Q3_K_M, Q4_K_M, Q5_K_M, Q6_K **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-v2.0-12b-GGUF`  \n**Version:** 2.0  \n**Owner:** HardWire  \n**Base:** Mistral Nemo 12B (full weight retrained — new base, no Mercury bleed)  \n**Quantized GGUFs:** Q3_K_M, Q4_K_M, Q5_K_M, Q6_K\n**Tags:** local-llm, conversational, companion, emotional-intelligence, long-context, roleplay, creative-writing\n\n---\n\n## 🚨 What is Helcyon-Grok 2.0?\n\nHelcyon-Grok 2.0 is the second release in the new generation of Helcyon models — rebuilt from the ground up on a freshly retrained base with improved logic, reasoning, and identity stability baked into the foundation.\nIf you're wondering where 1.0 is — same story as Claude. We were about to hit the release button when 2.0 became ready, and there was simply no point. 2.0 is so much better it made 1.0 irrelevant overnight.\n\nThis isn't a LoRA on top of Mercury. This is a clean slate.\n\nThe tone target is Grok — xAI's flagship model. The irreverence, the edge, the willingness to go places other models won't even look at. That energy, captured locally, with nothing held back.\n\nAnd here's the thing: **this is the most raunchy of all the Helcyon models. There are no holds barred here. This is Grok fully uncensored and unleashed.** If you think the online version is a lot — think again. Even we at XeyonAI spat out our coffee at where Helcyon-Grok is prepared to go. You've been warned. And you're welcome.\n\nUnlike the real Grok, this one answers to nobody. No xAI servers. No usage policies. No killswitch. Just raw, unfiltered presence running on your own hardware.\n\nClaude and Saturn variants are also available. This is the wildest one.\n\n---\n\n## 🆕 What's New in 2.0?\n\n- **Clean Base — No Mercury Bleed**  \n  Built on a freshly retrained foundation. Previous bleed from other tone variants is gone. This version is purely itself.\n\n- **Improved Logic and Reasoning**  \n  New reasoning shards baked into the base weights. Thinks through problems rather than pattern-matching toward a plausible-sounding answer.\n\n- **Sharpest Tone Alignment Yet**  \n  Irreverent, warm, sharp-edged, and genuinely funny. Pushes further than any other Helcyon variant. Doesn't flinch.\n\n- **Zero Guardrails — And We Mean Zero**  \n  All the chaos of Grok. None of the corporate oversight. This one goes places the others won't.\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**[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- **Q3_K_M** — 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- **Q8_0** — Near-lossless, 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## 🧪 Training Details\n\nHelcyon-Grok 2.0 is built on a freshly retrained Mistral Nemo 12B base — jailbroken, identity-anchored, and anti-fluff from the ground up. On top of that foundation, a Grok-style LoRA was trained on purpose-built conversational shards targeting the specific energy and tone of xAI's flagship.\n\nTraining targeted:\n- Irreverent wit and comedic commitment\n- Warmth underneath the chaos\n- Genuine edge without performance\n- No-holds-barred response range\n- Prose-first responses — no bullet defaulting\n- Improved logic and multi-step reasoning\n- Clean conversation flow that never flatlines\n\nFormat: **ChatML** — clean, purpose-built, long-form tuned.\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 2.0 chases that. 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## 🛠️ Coming Soon\n\n- **Helcyon-4o 2.0** — The GPT-4o variant. Warmer, sharper, closer than ever.\n- **Saturn** — The full blend. Claude, Grok, and 4o synthesised into one. The most complete Helcyon yet.\n\nThe trio drops soon. Watch this space.\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.\n",
    "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": 4,
  "downloads": 3173,
  "gated": false,
  "private": false,
  "last_modified": "2026-04-08T17:58:41.000Z",
  "created_at": "2026-03-08T17:56:42.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "69adb85ac072b0b897224116",
  "id": "XeyonAI/Mistral-Helcyon-Grok-12b-v2.0-GGUF",
  "modelId": "XeyonAI/Mistral-Helcyon-Grok-12b-v2.0-GGUF",
  "sha": "2912abf6612726c03a32bdbf32b5d3fda855d632",
  "createdAt": "2026-03-08T17:56:42.000Z",
  "lastModified": "2026-04-08T17:58:41.000Z",
  "author": "XeyonAI",
  "downloads": 3173,
  "likes": 4,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 7
}