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 Aug 3, 2026Llama 3.1 Euryale 70B v2.2 is a 70.6-billion-parameter text model from the community fine-tuning scene, released under a non-commercial licence with a 131,072-token request limit. Its weights can be downloaded, but the licence forbids commercial use.
Pick this for long-context text generation or analysis at 131,072 tokens, or for non-commercial projects where symmetric pricing across input and output simplifies cost prediction. Use it on hosts where the listed throughput meets your speed needs. Skip it if you need a commercial licence, measured quality scores, or multimodal input.
The case for it
- 131,072-token request limit for a 70.6-billion-parameter open model, with no mixture-of-experts reduction — the full model runs throughout.
- Symmetric input and output rates on most tracked hosts, which simplifies cost prediction for projects with balanced token flows.
The case against it
- Non-commercial licence sharply limits deployment options, unlike the Apache or MIT licences common among downloadable models.
- No measured benchmark scores in our data — no Elo, MMLU or other scores to verify quality claims.
- Verified throughput varies sharply between hosts, with the slowest listed option also priced higher.
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 Llama 3.1 Euryale 70B v2.2 — 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 4 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
- $0.85 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 |
|---|---|---|---|---|---|---|
| OpenRouter | $0.85 / $0.85 | 131K | not measured | Unknown | Unknown | Unknown |
| DeepInfrafp8 | $0.85 / $0.85 | 131K | not measured | Unknown | Unknown | Unknown |
| DeepInfrafp8 | $0.85 / $0.85 | 131K | 35 tok/s | No | No | Confirmed |
| Novita AIfp8 | $1.45 / $1.45 | 8K | 34 tok/s | No | No | Confirmed |
DeepInfra
Novita AIAcross the 4 listings we hold: 2 say they do not train on prompts, 0 say they do and 2 do not say. 2 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 | ✓ | ✓ | ✓ |
| DeepInfrafp8 | |||
| DeepInfrafp8 | ✗ | ✓ | ✓ |
| Novita AIfp8 | ✓ | ✗ | ✓ |
Tool calling: 2 of 4 listings say yes, 1 says no, 1 publishes no parameter list. JSON output: 2 of 4 listings say yes, 1 says no, 1 publishes no parameter list. Strict schema: 3 of 4 listings say yes, 1 publishes no parameter list.
Models people weigh against Llama 3.1 Euryale 70B v2.2
When we formed this view
Dates behind this page
Prices last checked 38h 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.
- 1 of 4 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 4 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 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
- Modality record
- text->text
- Catalogue slug
- sao10k-llama-3-1-euryale-70b-v2-2