Hermes 4 405B
Nous Research · released Aug 6, 2025 · NousResearch/Hermes-4-405B
- Type
- Open weightsLlama 3 Community License
- Params
- 406B
- Context
- 131K
about 98K words of context · download allowed, licence restricts use
Our take
Written Sep 4, 2026Hermes 4 is a 406-billion-parameter text-only model from Nous Research, released in 2025 under a restricted community licence. It is among the largest downloadable chat models we list, though no quality scores are available yet.
Pick this when you specifically need a 400-billion-plus open-weights model for text tasks, or when 131,072 tokens of context in a downloadable model at this scale matters. Use it only if your case fits the licence: research or personal use, or you have over 700 million monthly users and can negotiate with Meta. Skip it if you need measured quality data, multimodal input, or a permissive commercial licence.
The case for it
- 406 billion total parameters — among the largest open-weights releases we list.
- Identical pricing across both tracked providers.
- Known throughput of 36 tokens per second on Nebius.
The case against it
- No benchmark scores in our data: chat, reasoning, coding and safety are all unverified.
- Llama 3 Community Licence blocks commercial use unless you have over 700 million monthly users and negotiate with Meta.
- Dense architecture with 406 billion active parameters and no claimed sparsity means high inference cost per token.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M3 Ultra (80-core GPU) · 512 GB
Room to spare. 118.1 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 2 hours ago — each listing carries its own date.
- per 1M tokens
- $1.00 in / $3.00 out
- Context served
- 131K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $1.00 / $3.00checked 2 hours ago | 131K | not measured | Unknown | Unknown | Unknown |
| Nebius AI Studiofp8Through OpenRouter | $1.00 / $3.00checked 2 hours ago | 131K118K max reply | 21 tok/s | No | No | Confirmed |
Nebius AI StudioAcross the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 1 appears in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✗ | ✓ | ✗ |
| Nebius AI Studiofp8Through OpenRouter | ✗ | ✓ | ✗ |
Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 2 of 2 listings say yes. Strict schema: 0 of 2 listings say yes, 2 say no.
Models people weigh against Hermes 4 405B
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No independent board has scored it, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsLlama 3 Community License, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Llama 3 Community License
Commercial use allowed below 700M MAU; requires "Built with Meta Llama 3" attribution and Llama naming on derivatives.
Identifiers
- Hugging Face
- NousResearch/Hermes-4-405B
- Architecture
- Dense
- Takes in, gives back
- Text in, text out
- Catalogue slug
- nousresearch-hermes-4-405b