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 Sep 4, 2026Hermes 4 is a 70.6-billion-parameter text-only chat model from Nous Research with a 131,072-token request limit. Its weights can be downloaded under a restricted community licence, and two hosts offer identical rates.
Pick this for long-context text work at 131,072 tokens where downloadable weights matter, or when you want predictable pricing across the two tracked hosts. Use it on Nebius if 66 tokens per second suits your pace. Skip it if you need measured quality scores, multimodal input, or a licence that permits unrestricted commercial use at any scale.
The case for it
- 70.6 billion parameters, a substantial scale for a downloadable chat model.
- 131,072-token request limit is very long for the open-weights class.
- Identical pricing across both tracked hosts, so provider choice does not affect cost.
The case against it
- No benchmark scores, Elo, or other measured quality data in our records.
- Throughput is unverified on OpenRouter; only Nebius lists a figure.
- Llama 3 Community Licence restricts commercial use above 700 million monthly active users; not as permissive as Apache or MIT.
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.
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.
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 between 22 days and 23 days ago — each listing carries its own date.
- 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 |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.13 / $0.40checked 22 days ago | 131K | not measured | Unknown | Unknown | Unknown |
| Nebius AI Studiofp8Through OpenRouter | $0.13 / $0.40checked 23 days ago | 131K | not measured | No | No | Unknown |
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. 0 appear 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 70B
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-4-70B
- Architecture
- Dense
- Takes in, gives back
- Text in, text out
- Catalogue slug
- nousresearch-hermes-4-70b