Llama 3.3 Euryale 70B
Sao10K · released Dec 7, 2024 · Sao10K/L3.3-70B-Euryale-v2.3
- 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 3, 2026Llama 3.3 Euryale 70B is a 70.6-billion-parameter text-only model released in late 2024 with a 131,072-token request limit. It is available under the Llama 3 Community License for teams that need long-context open-weight inference, though no benchmark scores are available to verify its quality.
Pick this for long-context text tasks at 131,072 tokens where downloadable weights matter and the Llama 3 Community License terms are acceptable. It suits budget-conscious inference with identical rates across its two providers. Skip it if you need measured quality data, a permissive licence like Apache 2.0, or more than two hosting options to choose from.
The case for it
- 131,072-token request limit, among the longer contexts in open-weights models at this scale.
- Identical pricing across both tracked providers.
The case against it
- No benchmark scores in our data, so quality claims are unverified.
- Throughput is unmeasured on one of its two providers.
- Llama 3 Community License carries commercial restrictions, less permissive than Apache 2.0.
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 4 hours and 16 hours ago — each listing carries its own date.
- per 1M tokens
- $0.65 in / $0.75 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 | $0.65 / $0.75checked 4 hours ago | 131K | not measured | Unknown | Unknown | Unknown |
| NextBitbf16Through OpenRouter | $0.65 / $0.75checked 16 hours ago | 131K16K max reply | 11 tok/s | No | No | Confirmed |
Across the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 1 appears 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 | ✗ | ✓ | ✓ |
| NextBitbf16Through OpenRouter | ✗ | ✓ | ✓ |
Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
Models people weigh against Llama 3.3 Euryale 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
- Sao10K/L3.3-70B-Euryale-v2.3
- Architecture
- Dense
- Takes in, gives back
- Text in, text out
- Catalogue slug
- sao10k-llama-3-3-euryale-70b