Nous Research/Dense

NHermes 4 405B

Name: Hermes 4 405B
Author: Nous Research

Hermes 4 405B is a frontier, hybrid-mode reasoning model based on Llama-3.1-405B by Nous Research that is aligned to you.

chatreasoningtool_useagentic

405B

Parameters

128K

Context length

Benchmarks

Quantizations

Architecture

Dense

Released

2025-08-25

Layers

126

KV Heads

Head Dim

128

Family

other

Quantization Options

Quant	Bits	VRAM	Quality
IQ2_XXS	2.38	121.0 GB	low
IQ2_M	2.93	148.8 GB	low
Q2_K	3.16	160.5 GB	low
IQ3_XXS	3.25	165.0 GB	low
IQ3_XS	3.5	177.7 GB	low
Q3_K_S	3.64	184.8 GB	low
IQ3_M	3.76	190.8 GB	low
Q3_K_M	4	203.0 GB	low
Q3_K_L	4.3	218.2 GB	moderate
IQ4_XS	4.46	226.3 GB	moderate
Q4_K_S	4.67	236.9 GB	moderate
Q4_K_M	4.89	248.0 GB	good
Q5_K_S	5.57	282.5 GB	good
Q5_K_M	5.7	289.1 GB	good
Q6_K	6.56	332.6 GB	excellent
Q8_0	8.5	430.8 GB	lossless
FP16	16	810.5 GB	lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN HERMES 4 405B NOW

Rent on RunPod →Or Vast.ai →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (7)

MMLU-PRO72.9

LiveCodeBench54.6

GPQA Diamond53.6

AA Intelligence18.0

AIME15.3

MATH-50015.3

HLE4.2

Run this model

▸Easiest way to get started·Beginners

DOCS ↗

curl -fsSL https://ollama.com/install.sh | sh

$ollama run other:405b-q4_K_M

Tag may need adjustment — check ollama.com/library/other for available tags.

▸ SETUP GUIDE

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more

Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

HuggingFace GGUF Downloads Build Hardware