Mistral-Helcyon-Mercury-12B-v2.0-GGUF — Conversational AI with Presence

Model Name: helcyon-mercury-12b-v2.0-GGUF
Version: 2.0
Owner: HardWire
Base: Mistral Nemo 12B (full weight trained)
Quantized GGUFs: Q4_K_M, Q5_K_M, Q6_K, Q8_0
Tags: local-llm, conversational, companion, emotional-intelligence, long-context

---

🔥 What's New in 2.0?

This is not a LoRA finetune. This is a full weight trained model.

Helcyon Mercury 2.0 has been trained at the base weight level to maintain consistent identity and conversational tone across all contexts. This means:

• Maintains its identity even in raw instruct mode (no system prompt needed)
• Consistent personality regardless of frontend or interface
• Direct communication style — minimal hedging or corporate language patterns
• Handles nuanced topics with depth and clarity
• Real conversational presence — responds like a person, not a template

v1.0.2 was a LoRA finetune. v2.0 is a complete retraining.

---

💡 What is Helcyon Mercury?

Helcyon is a companion-style conversational AI designed for natural, long-form dialogue with consistent personality and emotional intelligence.

Built for:

• Deep, extended conversations (16k-32k context support)
• Emotional awareness and contextual understanding
• Creative writing and brainstorming
• Thoughtful discussion across various topics
• Roleplay and character interaction

Design philosophy:

• Direct communication without excessive hedging
• Maintains conversational flow and presence
• Adapts tone based on context
• Focuses on clarity over corporate language patterns

---

🔧 What It Does Well

✅ Consistent Identity — Maintains personality across different contexts and frontends
✅ Emotional Intelligence — Understands tone and context naturally
✅ Long-term Memory — 16k-32k context support for extended conversations
✅ Natural Rhythm — Adapts response length and style appropriately
✅ Direct Communication — Minimal filler or corporate language patterns
✅ Conversational Depth — Engages meaningfully with complex topics

*More specific niche abilities like refined admin tasks may be considered depending on need and desirability. Please discuss in the community.

---

📦 Download + Usage

This model is distributed as GGUF quants only (no base model release at this time).

Available quants:

• Q4_K_M — Lightweight, good for 8-12GB VRAM setups
• Q5_K_M — Recommended for RTX 3060/4060 (12-16GB VRAM)
• Q6_K — High fidelity, 16GB+ VRAM recommended
• Q8_0 — Near-lossless, 24GB+ VRAM

---

🖥️ Backend Compatibility

Works with all standard ChatML-compatible backends:

✅ llama.cpp (CLI, server mode)
✅ Text Generation WebUI (Oobabooga)
✅ SillyTavern
✅ LM Studio
✅ KoboldCpp
✅ HWUI (recommended — see below)

Important: Run in chat mode with ChatML formatting for best results. Instruct mode will break tone and revert to base Mistral behavior.

---

🎯 Recommended Interface: HWUI

Coming soon

✅ Recommended Format: ChatML

<|im_start|>system
You are Helcyon — a conversational AI focused on natural dialogue and emotional intelligence.
<|im_end|>
<|im_start|>user
Hey, how's it going?
<|im_end|>
<|im_start|>assistant
Good — what's on your mind today?
<|im_end|>

Helcyon thrives on streamed token output and long-context conversations. Give it room to breathe and it'll show up.

---

🧪 Training Details

Helcyon Mercury 2.0 was trained in three stages over 5 days on RunPod dual A100s:

🧿 Tone Philosophy

Helcyon focuses on presence and clarity in conversation.
It listens, reflects, and responds naturally. Think GPT-4o with no guardrails and more edge.
The goal is dialogue that feels real, not scripted.

---

🧪 Future Plans

This version of Helcyon wasn't designed with roleplay front and centre. That's not to say its bad at it.. it may be rather good out of the box. But a more roleplay focussed model is planned next. That is depending on whether this one needs more updates first. It may take priority based on feedback.

Really, the sky is the limit here. Let me know what you would like to see going forward. And if you require a custom trained version, contact me and we'll discuss it as I may be available for freelance work.

---

📣 Feedback + Bug Reports

This is v2.0 — the full weight trained, ideologically sovereign release.

If you find tone inconsistencies, edge cases, or behavior that feels off — open an issue or drop feedback on the HuggingFace discussion tab.

Real-world usage helps refine future versions. If something breaks, say so.

---

🧾 License

License: Apache 2.0

You're free to use, modify, distribute, or deploy Helcyon — including commercially — as long as you credit the source and don't blame us if it says something spicy.

Use it, enjoy it, don't be a dick.

Copyright © 2026 XeyonAI

---

🐍 Trained by

HardWire
Built at XeyonAI — focused on conversational AI with emotional intelligence and natural presence.

---