Hermes 4 70B
Nous Research · released Aug 18, 2025 · NousResearch/Hermes-4-70B
- Type
- Open weightsLlama 3 Community License
- Params
- 70.6B
- Context
- 131K
about 98K words of context · download allowed, licence restricts use
Our take
Written Aug 3, 2026Hermes 4 is a 70.6-billion-parameter text-only chat model from Nous Research with a 131,072-token request limit and a restricted community licence. It is a long-context option for teams who need downloadable weights, though no quality scores have been measured yet.
Pick this for long-context text work up to 131,072 tokens where open weights matter more than a permissive licence, or for budget-conscious 70-billion-parameter inference when the Llama 3 Community terms fit your use case. Skip it if you need measured quality data, a truly unrestricted licence for large-scale commercial use, or multimodal input.
The case for it
- 131,072-token request limit — among the longest disclosed for 70-billion-parameter-scale open models.
- Two tracked hosting options with identical pricing, giving some provider choice.
The case against it
- No measured quality or capability scores: chat, reasoning, coding and safety performance are all unverified in our data.
- Restricted licence triggers platform and scale obligations at 700 million users, unlike Apache or MIT alternatives.
- Throughput is unverified on one of two tracked hosts.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up Hermes 4 70B — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
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.
Apple M1 Max (32-core GPU) · 64 GB
Borderline fit on an estimated size. It leaves 0.3 GB spare on a size we calculated rather than measured, and a 10% error either way would change the answer.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 2 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.13 in / $0.40 out
- Context served
- 131K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.13 / $0.40 | 131K | not measured | Unknown | Unknown | Unknown |
| Nebius AI Studiofp8 | $0.13 / $0.40 | 131K | 85 tok/s | No | No | Confirmed |
Nebius AI StudioAcross the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✗ | ✓ | ✗ |
| Nebius AI Studiofp8 | ✗ | ✓ | ✗ |
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 70B
When we formed this view
Dates behind this page
Prices last checked 5d ago
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 board we watch has turned up a score, 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 do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
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-4-70B
- Architecture
- Dense
- Modality record
- text->text
- Catalogue slug
- nousresearch-hermes-4-70b