Hermes 3 405B Instruct
Nous Research · released Aug 13, 2024 · NousResearch/Hermes-3-Llama-3.1-405B
- Type
- Open weightsLlama 3 Community License
- Params
- 406B
- Context
- 131K
about 98K words of context · download allowed, licence restricts use
Our take
Written Sep 5, 2026Hermes 3 is a 406-billion-parameter text-only instruction model from Nous Research, released in 2024 under Meta's Llama 3 Community License. It handles up to 131,072 tokens in a single request and is priced identically across all three tracked hosts.
Pick this when you need the largest Hermes-family model for long-context text work, or budget-sensitive access to a 400-billion-parameter instruct model. Use it if Llama 3 Community License terms fit your attribution and redistribution needs. Skip it if you need measured quality scores, multimodal input, or a fully permissive licence like Apache 2.0 or MIT.
The case for it
- Unusually low price for a 406-billion-parameter model, with all three offers priced the same.
- 131,072-token request limit, very large among open text models.
- One hosted endpoint discloses throughput at 15 tokens per second.
The case against it
- No benchmark scores of any kind in our data — no measured chat, coding or reasoning quality.
- Throughput unverified for two of three offers.
- Llama 3 Community License requires attribution and carries redistribution terms, less permissive than Apache 2.0 or MIT alternatives.
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 4 hours ago — each listing carries its own date.
- per 1M tokens
- $1.00 in / $1.00 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 / $1.00checked 4 hours ago | 131K | not measured | Unknown | Unknown | Unknown |
| DeepInfrafp8Direct and through OpenRouter | $1.00 / $1.00checked 4 hours ago | 131K16K max reply through OpenRouter | 18 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
DeepInfraAcross the 2 listings we hold: 1 says it does not train on prompts (only through OpenRouter), 0 say they do and 1 does not say. 1 appears in the zero-retention registry we check (only through OpenRouter); 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 | ✗ | ✓ | ✓ |
| DeepInfrafp8Direct and through OpenRouter | ✗ | ✓ | ✓ |
Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
Models people weigh against Hermes 3 405B Instruct
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, and 1 answers only through OpenRouter, not for its own listing.
- 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-3-Llama-3.1-405B
- Architecture
- Dense
- Takes in, gives back
- Text in, text out
- Catalogue slug
- nousresearch-hermes-3-405b-instruct