Hermes 4 405B

Nous Research · nous-research/hermes-4-405b

Provider	Nous Research
Family	hermes
Type	llm-chat
Status	active
Released	2025-08-06
Updated	2025-09-02
Parameters	405.9B
Open weights	yes

Lineage

Relationship	Model
Is a finetune of	meta-llama/Llama-3.1-405B

What it fits on

Ordered by predicted speed. Bandwidth sets decode rate; memory decides whether it runs at all.

Every figure here is computed, not measured. Fit is weights at each quantisation against device memory, with a 25% allowance for the KV cache, activations and the OS. Decode rate is the memory-bandwidth roofline at 70% efficiency. Nobody has run this model on these devices.

Device	Memory	Bandwidth	Best quality	Weights	tok/s	Fastest
NVIDIA GB200 Grace Blackwell Superchip	372.0 GB	16000.0 GB/s	q5	253.66 GB	~44.2	~55.2 q4
AMD Instinct MI355X	288.0 GB	8000.0 GB/s	q4	202.93 GB	~27.6	~27.6 q4
Apple M3 Ultra	512.0 GB	819.0 GB/s	q6	304.39 GB	~1.9	~2.8 q4

Where it runs

Taken from the card's availability section.

Platform	Id on that platform
Hugging Face	NousResearch/Hermes-4-405B

Verified benchmark evidence

Each row was checked against its source by a reviewer, and carries the model identifier as actually evaluated — which is not always the same as this card's.

Benchmark	Evaluated as	Score	Evidence date	Source kind
aa_lcr	Hermes 4 405B	22.33%	2026-09-10 evaluated	independent evaluator	source
critpt	Hermes 4 405B	0.29%	2026-09-10 evaluated	independent evaluator	source
gpqa_diamond	Hermes 4 405B	72.73%	2026-09-10 evaluated	independent evaluator	source

Reported benchmark scores

This card reports no benchmark scores yet.

Benchmark	Catalogue standing	Score

Data

This card as JSON · See it in the graph · Edit on GitHub