mythos-v2-8b-merged
Uncensored, agentic model — tool-use, shell & coding, zero refusals.
· Part of the **FableForge** ecosystem.
⚡ Quickest start — Ollama (these pulls credit the source, not a mirror)
ollama run hf.co/King3Djbl/mythos-v2-8b-merged:Q4_K_M
🦙 llama.cpp
llama-cli -hf King3Djbl/mythos-v2-8b-merged:Q4_K_M -p "Hello!"
💠 LM Studio
Search King3Djbl/mythos-v2-8b-merged and pick a quant below.
📦 Provided quants (download one file, not the whole repo)
| File | Quant | Size | Notes |
|---|---|---|---|
| mythos-v2-8b-F16.gguf | F16 | 16.39 GB | Full precision (unquantized). Reference / conversion. |
| mythos-v2-8b-Q8_0.gguf | Q8_0 | 8.71 GB | Extremely high quality — usually overkill. |
| mythos-v2-8b-Q6_K.gguf | Q6_K | 6.73 GB | Very high quality, near-perfect. Recommended if you have the RAM. |
| mythos-v2-8b-Q5_K_M.gguf | Q5_K_M | 5.85 GB | High quality. Recommended. |
| mythos-v2-8b-Q4_K_M.gguf | Q4_K_M | 5.03 GB | ⭐ Best size/quality balance — default pick for most users. |
| mythos-v2-8b-IQ4_XS.gguf | IQ4_XS | 1.80 GB | imatrix — great quality, smaller than Q4_K_S. Recommended for low RAM. |
| mythos-v2-8b-Q4_0.gguf | Q4_0 | 4.77 GB | Legacy format — prefer Q4_K_M. |
| mythos-v2-8b-Q3_K_M.gguf | Q3_K_M | 4.12 GB | Lower quality; usable when RAM is tight. |
| mythos-v2-8b-IQ3_XXS.gguf | IQ3_XXS | 3.37 GB | imatrix very low quality. |
| mythos-v2-8b-Q2_K.gguf | Q2_K | 3.28 GB | Very low quality — surprisingly usable. |
| mythos-v2-8b-IQ2_XXS.gguf | IQ2_XXS | 2.49 GB | Tiny imatrix — last resort. |
Not sure? Take Q4_K_M. Low RAM → IQ4_XS. Max quality → Q6_K.
🧠 Prompt format (ChatML)
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
🌌 See it live — the FableForge demos
This family powers a galaxy of free, interactive HF Spaces:
🔗 Related models
- 🔧 LoRA adapter:
mythos-v2-8b-lora
⭐ Like & share — it helps people find the source instead of a mirror.