Hermes 3 70B Instruct
Nous Research · released Jul 29, 2024 · NousResearch/Hermes-3-Llama-3.1-70B
- 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 2, 2026Hermes 3 is a 70.6-billion-parameter text model from Nous Research with a 131,072-token request limit and a restricted community licence. It suits long-context instruction tasks at budget pricing, though its reasoning scores are modest and the licence carries commercial limits.
Pick this for long-context text work where 131,072 tokens per request is enough and low per-token cost matters. Use it if you need solid instruction-following and already fit within the Llama 3 Community Licence terms. Skip it if you need graduate-level science reasoning, broad knowledge coverage, or freedom to redistribute modified weights.
The case for it
- 131,072-token request limit at matching input and output rates among the cheaper options we track.
- Strong measured instruction-following at 76.6% on the IFEval benchmark.
The case against it
- Weak graduate-level reasoning: only 14.9% correct on GPQA Diamond.
- Thin broad knowledge at 41.4% on MMLU-Pro.
- Licence restrictions: modified weights cannot be redistributed, and very large user bases must negotiate separate terms with Meta.
How good is it?
EverydayGeneral questions and everyday reasoning
Not yet scored on Arena Text (overall). It is on GPQA Diamond, in 6th of 16 with 36.2.
CodingWriting and fixing code on its own
Not yet scored on Arena Coding.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Not yet scored on Arena Creative Writing.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done.
Every published score for this model3 scoresEvery figure we hold, from 3 boards, with who ran it and a link to the source — including the boards no rating above is built on.
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 2 hours ago — each listing carries its own date.
- per 1M tokens
- $0.70 in / $0.70 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 | $0.70 / $0.70checked 2 hours ago | 131K | not measured | Unknown | Unknown | Unknown |
| DeepInfrafp8Direct and through OpenRouter | $0.70 / $0.70checked 2 hours ago | 131K16K max reply through OpenRouter | 26 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: 0 of 2 listings say yes, 2 say no. Strict schema: 2 of 2 listings say yes.
Models people weigh against Hermes 3 70B 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.
- 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-3.1-70B
- Architecture
- Dense
- Takes in, gives back
- Text in, text out
- Catalogue slug
- nousresearch-hermes-3-70b-instruct