Llama 3.1 Euryale 70B v2.2
Sao10K · released Aug 12, 2024 · Sao10K/L3.1-70B-Euryale-v2.2
- Type
- Open weightsCreative Commons Attribution-NonCommercial 4.0
- Params
- 70.6B
- Context
- 131K
about 98K words of context · download allowed, licence restricts use
Our take
Written Sep 2, 2026Llama 3.1 Euryale is a 70.6-billion-parameter text-only model built for creative writing and roleplay, with a 131,072-token request limit that suits long-form generation. Its weights can be downloaded, but the non-commercial licence blocks most business use.
Pick this for local or API-hosted creative projects where long context matters and the licence fits your purpose — the cheapest tracked rate is well under half the price of the fastest option. Use it for non-commercial research or hobby roleplay where 131K tokens of context is useful. Skip it if you need commercial deployment, measured quality scores, or any image or audio handling.
The case for it
- 131,072-token request limit — among the longer contexts in downloadable models at this scale.
- Lowest tracked rate is available from three separate listings, with a choice of throughput speeds.
The case against it
- Non-commercial licence prohibits most business use, monetised products and commercial integrations.
- No benchmark scores in our data — chat, reasoning, coding and other capabilities are unverified.
- Faster throughput costs markedly more per token than the cheapest option.
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 2 hours ago — each listing carries its own date.
- per 1M tokens
- $0.85 in / $0.85 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 | $0.85 / $0.85checked 2 hours ago | 131K | not measured | Unknown | Unknown | Unknown |
| DeepInfrafp8Direct and through OpenRouter | $0.85 / $0.85checked 2 hours ago | 131K16K max reply through OpenRouter | 35 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Novita AIfp8Through OpenRouter | $1.45 / $1.45checked 2 hours ago | 8K7K max reply | 35 tok/s | No | No | Confirmed |
DeepInfra
Novita AIAcross the 3 listings we hold: 2 say they do not train on prompts (1 of them only through OpenRouter), 0 say they do and 1 does not say. 2 appear in the zero-retention registry we check (1 of them 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 | ✗ | ✗ | ✓ |
| Novita AIfp8Through OpenRouter | ✓ | ✗ | ✓ |
Tool calling: 2 of 3 listings say yes, 1 says no. JSON output: 0 of 3 listings say yes, 3 say no. Strict schema: 3 of 3 listings say yes.
Models people weigh against Llama 3.1 Euryale 70B v2.2
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 3 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 allowsCreative Commons Attribution-NonCommercial 4.0, 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
Creative Commons Attribution-NonCommercial 4.0
Weights are downloadable but commercial use is prohibited. Research and personal use only.
Identifiers
- Hugging Face
- Sao10K/L3.1-70B-Euryale-v2.2
- Architecture
- Dense
- Takes in, gives back
- Text in, text out
- Catalogue slug
- sao10k-llama-3-1-euryale-70b-v2-2