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) 🦙 llama.cpp 💠 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 usab…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy