20+ models
Ollama repack of Qwen3.6-35B-A3B Genesis Hermes V7 with APEX/APEX-Compact, Vision, and 224K context for coding agents.
Hermes 3 3B is a small but mighty new addition to the Hermes series of LLMs by Nous Research, and is Nous's first fine-tune in this parameter class.
NousResearch/Hermes-3-Llama-3.1-8B Korean q4 model with CPT->SFT->DPO
NousResearch/Hermes-3-Llama-3.1-8B Korean q8 model with CPT->SFT->DPO
NousResearch/Hermes-3-Llama-3.1-70B Korean q4 model with CPT->SFT->DPO
NousResearch/Hermes-3-Llama-3.1-70B Korean q5 model with CPT->SFT->DPO
Llama-3.1-Storm-8B outperforms both Llama-3.1-8B-Instruct and Hermes-3-Llama-3.1-8B! 🤗 Blog: https://huggingface.co/blog/akjindal53244/llama31-storm8b
NousResearch/Hermes-3-Llama-3.1-405B
NousResearch/Hermes-3-Llama-3.1-8B in Ollama
Outperforms Llama-3.1-8B-Instruct and Hermes-3-Llama-3.1-8B
Llama-3.1-Storm-8B outperforms both Llama-3.1-8B-Instruct and Hermes-3-Llama-3.1-8B!
Nous Hermes 4.3 36B parameters with thinking and tools enabled
Hermes 4.3 36B (Q8_0) with the correct Llama-3 template — verified tools + thinking capabilities for agent use.
This is the llama.cpp GGUF Quantised version of Hermes 2 Pro Llama-3 8B from Nous Research with function calling capabilities.
NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF
Hermes 2 Pro - Llama-3 70B (f16.q4 and .q5)
Carnice Qwen3.6 35B-A3B (APEX I-Quality, agentic-tuned) wrapped with a baked-in 5-rule discipline SYSTEM prompt for Hermes-Agent orchestrator use. 22GB GGUF, ~24GB VRAM, qwen3.5 chat template.
somewhat uncensored, and quite creative.