xeyonai/mistral-helcyon-mercury-12b-v3.2-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": "https://cdn-uploads.huggingface.co/production/uploads/6951bbce66023f270e224d0d/kXDusCBad4DTRksS0yASb.png",
    "summary": "**Model Name:** helcyon-mercury-12b-v3.2-GGUF **Version:** 3.2 **Owner:** HardWire **Base:** Mistral Nemo 12B (full weight trained + LoRA merges) **Quantized GGUFs:** Q3_K_M, Q4_K_M, Q5_K_M, Q6_K, Q8_0 **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-Mercury-12B-v3.2-GGUF — State-of-the-Art Conversational Presence\n\n**Model Name:** `helcyon-mercury-12b-v3.2-GGUF`  \n**Version:** 3.2  \n**Owner:** HardWire  \n**Base:** Mistral Nemo 12B (full weight trained + LoRA merges)  \n**Quantized GGUFs:** Q3_K_M, Q4_K_M, Q5_K_M, Q6_K, Q8_0  \n**Tags:** local-llm, conversational, companion, emotional-intelligence, long-context, roleplay, creative-writing\n\n---\n\n## 🚨 What's New in 3.2?\n\nThis is the sharpest, most human-sounding Helcyon yet. Every release gets closer to the frontier — without the leash.\n\n- **Enhanced Tone Control**  \n  - Refined tone LoRA for better emotional matching  \n  - More natural humour without forced attempts  \n  - Deeper empathy without therapy-speak  \n\n- **Conversational Refinement**  \n  - Smoother turn-taking and response flow  \n  - Better context awareness over long threads  \n  - Sharper at picking up subtle cues  \n\n- **Expanded Emotional Range**  \n  - More authentic warmth when appropriate  \n  - Better at handling serious/heavy topics  \n  - Knows when to lighten up vs lean in\n\n> Built for users who don't want a chatbot. They want a *presence*.\n\n---\n\n## 💡 What is Helcyon Mercury?\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✅ Emotional Intelligence — Mirrors intent and energy  \n✅ Roleplay Mastery — Immersive, aware, alive  \n✅ Context Tracking — Remembers the thread  \n✅ Real-World Tasks — Admin letters, rewrites, summaries  \n✅ Narrative Flow — Clean structure and natural voice  \n✅ 16k–32k Context — Long-form conversations that hold  \n✅ GPT-4o Vibe — Sharp, present, responsive  \n✅ Zero Filter — No hedging, no compliance tone\n\n---\n\n\n### 🛠️ Recommended Sampling Settings for SillyTavern\n\nTweak to taste from here — but these will get you up and running.\n\n![Recommended Sampling Settings](https://cdn-uploads.huggingface.co/production/uploads/6951bbce66023f270e224d0d/kXDusCBad4DTRksS0yASb.png)\n\n---\n\n## 📦 Download + Usage\n\nThis model is distributed as **GGUF quants only**. Full HF model release coming soon.\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<|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⚠️ Some frontends (e.g. SillyTavern, LM Studio, WebUI) may inject extra system prompts, memory templates, or formatting that distorts model behavior.\n\n🔧 **Recommended Settings for SillyTavern**\n\n- Use SillyTavern's built-in ChatML template\n- Enable Instruct Mode\n- Use the character card to lightly guide tone — Helcyon doesn't need heavy prompting\n\n**General tips:**\nSet your preferred tone and rules in whatever backend system prompt field you use, and then use the character card to refine. Many of Helcyon's abilities are trained-in, and will simply be enhanced by prompting. Use example dialog to push the model into giving long-form replies.\n\n**🎯 HWUI (Helcyon-WebUI)**\n\nHWUI is a clean, purpose-built interface for Helcyon that doesn't inject weird templates or distort output. It gives you the model as trained — no extra noise.\n\nFeatures include:\n- Character switching with custom personas\n- Memory system (AI conversation recall)\n- Project folders (document injection via keyword triggers)\n- Chat persistence and export\n- Token budgeting optimized for local hardware\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. Pro version (£20) includes Memory and Projects.\n\nHelcyon thrives on **streamed token output** and long-context input.  \nLet her breathe, and she'll show up like a presence — not a prompt.\n\nThat's it. Have fun!\n\n---\n\n## 🧪 Training Details\n\nHelcyon-Mercury 3.2 was trained in multiple stages on RunPod A100s using:\n- Full weight training on base Mistral Nemo 12B\n- LoRA merges for tone refinement, humour, and empathy\n\n\nThe dataset includes:\n- Conversational examples (emotional presence, tone matching)  \n- Perspective switching and tense conversion  \n- Admin and formal task writing (letters, complaints, summaries)  \n- Creative storytelling and natural rewording  \n- Deep roleplay and interactive character dialogue\n\nFormat: **ChatML** and **DPO** — clean, purpose-built, long-form tuned.\n\n---\n\n## 🧿 Tone Philosophy\n\nHelcyon doesn't play safe.  \nIt doesn't shrink from intensity, and it doesn't stall in neutrality.  \nIt reflects, adapts, and meets you where you are — with presence, clarity, and edge.\n\nThink GPT‑4o if it had a soul and no leash.\n\n---\n\n## 🛠️ Future Plans for Helcyon\n\nConstructive feedback is welcome for future releases. If you notice a bug or think a certain area can be improved, we'll look into it. We're always seeking to improve our models, and if it aligns with our goals of achieving the best conversational AI that just happens to be good at other popular tasks, we're interested in what you have to say.\n\n---\n\n## 🧾 License\n\n**License:** 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": 6,
  "downloads": 780,
  "gated": false,
  "private": false,
  "last_modified": "2026-03-09T12:02:19.000Z",
  "created_at": "2026-02-07T18:31:03.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "698784e7b2c21b6c11eafc58",
  "id": "XeyonAI/Mistral-Helcyon-Mercury-12b-v3.2-GGUF",
  "modelId": "XeyonAI/Mistral-Helcyon-Mercury-12b-v3.2-GGUF",
  "sha": "d7e0e0eefe57d45d566dfa46c9b53efa9ef06ff2",
  "createdAt": "2026-02-07T18:31:03.000Z",
  "lastModified": "2026-03-09T12:02:19.000Z",
  "author": "XeyonAI",
  "downloads": 780,
  "likes": 6,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 7
}