Hermes · Ollama

hermes3

Hermes 3 is the latest version of the flagship Hermes series of LLMs by Nous Research

tools 3b 8b 70b 405b

1.7M Pulls 65 Tags Updated 1 year ago

openhermes

OpenHermes 2.5 is a 7B model fine-tuned by Teknium on Mistral with fully open datasets.

1.2M Pulls 35 Tags Updated 2 years ago

nous-hermes2-mixtral

The Nous Hermes 2 model from Nous Research, now trained over Mixtral.

8x7b

595.8K Pulls 18 Tags Updated 1 year ago

nous-hermes2

The powerful family of models by Nous Research that excels at scientific discussion and coding tasks.

10.7b 34b

1.1M Pulls 33 Tags Updated 2 years ago

nous-hermes

General use models based on Llama and Llama 2 from Nous Research.

7b 13b

1.2M Pulls 63 Tags Updated 2 years ago

edtorre/qwen3.5-hermes

A compact, agent-tuned Qwen 3.5 model built for local agent harnesses like Hermes Agent. Based on `qwen3.5:latest` with Q4_K_M quantization for a lightweight 6.6 GB footprint, while retaining strong tool-calling, vision, and thinking capabilities.

vision tools thinking

2,226 Pulls 1 Tag Updated 2 months ago

ericli1018/Hermes3.6-35B-A3B-Uncensored-Genesis-V7

Ollama repack of Qwen3.6-35B-A3B Genesis Hermes V7 with APEX/APEX-Compact, Vision, and 224K context for coding agents.

vision

1,124 Pulls 3 Tags Updated 1 month ago

steelpuddles/hermes-4.3-36B

Nous Hermes 4.3 36B parameters with thinking and tools enabled

tools thinking

2,203 Pulls 2 Tags Updated 4 months ago

refinedneuro/vibethinker-3b-hermes

Fine Tuned For Hermes-style function calling with VibeThinker 3b

tools

1,287 Pulls 7 Tags Updated 2 months ago

edtorre/gemma4

Gemma 4 12B agent-tuned for Hermes Agent and other local agent harnesses. One built for 20GB GPUs the other for 8GB GPUs.

vision tools thinking

1,077 Pulls 2 Tags Updated 2 months ago

edtorre/qwen3.6-hermes

Qwen 3.6 27B (Q4_K_M) optimized for Hermes Agent — 64K context, 8192 max tokens, MTP for speed, flash attention + Q8 KV cache.

vision tools thinking

961 Pulls 1 Tag Updated 2 months ago

mitcheffendi/qwen3.5-hermes-discipline-96k

My personal Hermes Agent-focused model configs for Qwen3.5:9b. Based on edtorre's work.

vision tools thinking

229 Pulls 1 Tag Updated 1 month ago

MonomythDevelopment/hermes-4.3-36b-tools

Hermes 4.3 36B (Q8_0) with the correct Llama-3 template — verified tools + thinking capabilities for agent use.

tools thinking

325 Pulls 1 Tag Updated 3 months ago

edtorre/gemma4-31b-hermes

Gemma 4 31B (Q4_0) optimized for Hermes Agent — 64K context, 8192 max tokens, flash attention + Q8 KV cache. Fits 24 GB VRAM with optimizations.

vision tools thinking

225 Pulls 1 Tag Updated 2 months ago

studiobrn/modOmniCoder

modOmniCoder is an agent-based, code-focused engineering assistant optimized for use alongside Claude Code and Hermes in hybrid development workflows.

tools thinking

229 Pulls 1 Tag Updated 3 months ago

AgentBDW/GIR9b

CTA agent for Claude Code / OpenCode / Hermes with the only command of follow instructions. Tested with 16GB of VRAM with a Context of 64k to avoid OOM with a 680M AMD iGPU =O) Results of 40~45 TPS using redis to queue requests. QWEN:9B What's next...!!!!

tools

98 Pulls 1 Tag Updated 2 months ago

elementsboutique88/Hermes-Cloud-Agent

tools

74 Pulls 1 Tag Updated 4 months ago

edtorre/muse-glimmer-agent

a 27.9B vision-language model tuned for Hermes and other agentic workflows.

vision tools

29 Pulls 1 Tag Updated 1 month ago

edtorre/lightning-agent

Lightning Agent — a 32.9B Nemotron MoE model tuned for Hermes agentic workflows.

tools

26 Pulls 1 Tag Updated 1 month ago

dlasher/Hermes-4.3-36B-GGUF

3 Pulls 1 Tag Updated 2 weeks ago