Llama 3.1 70B Instruct
Meta · released Jul 16, 2024 · meta-llama/Meta-Llama-3.1-70B-Instruct
- Type
- Open weightsLlama 3.1 Community License
- Params
- 70.6B
- Context
- 131K
about 98K words of context · download allowed, licence restricts use
Our take
Written Aug 3, 2026Llama 3.1 is a 70.6-billion-parameter text model from Meta, released in 2024 with a restricted community licence. It handles long requests and is widely available from hosts, though its benchmark scores vary sharply by task and its licence is less flexible than truly open alternatives.
Pick this for long-context text work up to 131,072 tokens, or when you need Llama-ecosystem access with broad provider choice. Use it if you want the cheapest rate among its own five tracked offers, which is half the price of the most expensive one. Skip it if you need graduate-level science reasoning, truly permissive licensing, or consistent quality across every task type.
The case for it
- Broad provider availability: five tracked offers with the cheapest rate exactly half the price of the most expensive.
- Strong measured instruction-following capability, at 86.7% on IFEval.
- Highest measured throughput among its own endpoints, at 27 tokens per second on CoreWeave versus 17–23 elsewhere.
The case against it
- Weak on graduate-level reasoning and science: 14.2% on GPQA Diamond, its lowest benchmark score.
- Arena performance varies widely by task type, with a 75.87-point spread from its best task to its worst.
- Restricted licence limits flexibility compared with truly permissive alternatives such as Apache 2.0 or MIT models.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)126th of 143 · 1293.3
CodingWriting and fixing code on its own
Arena Coding125th of 143 · 1333.1
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Llama 3.1 70B Instruct for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Llama 3.1 70B Instruct placed and give it no mark out of five.
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, which is why they get no rating.
Every published score for this model9 scoresEvery figure we hold, from 9 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?
- 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 0.6 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 5 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
- $0.40 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 |
|---|---|---|---|---|---|---|
| OpenRouter | $0.40 / $0.40 | 131K | not measured | Unknown | Unknown | Unknown |
| DeepInfrafp8 | $0.40 / $0.40 | 131K | 23 tok/s | No | No | Unknown |
| DeepInfraturbo tierfp8 | $0.40 / $0.40 | 131K | 19 tok/s | No | No | Unknown |
| Amazon Bedrock | $0.72 / $0.72 | 131K | 21 tok/s | No | No | Confirmed |
| CoreWeavebf16 | $0.80 / $0.80 | 128K | 27 tok/s | No | No | Confirmed |
DeepInfra
Amazon BedrockAcross the 5 listings we hold: 4 say they do not train on prompts, 0 say they do and 1 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 | ✓ | ✓ | ✓ |
| DeepInfraturbo · fp8 | ✓ | ✓ | ✓ |
| Amazon Bedrock | ✗ | ✗ | ✗ |
| CoreWeavebf16 | ✗ | ✓ | ✓ |
Tool calling: 3 of 5 listings say yes, 2 say no. JSON output: 4 of 5 listings say yes, 1 says no. Strict schema: 4 of 5 listings say yes, 1 says no.
Models people weigh against Llama 3.1 70B Instruct
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.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 5 listings do not say whether they train on prompts.
Licence and identifiers
What the licence allowsLlama 3.1 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 3.1 Community License
Commercial use below 700M MAU. Notably allows using outputs to improve other models, which earlier Llama licenses banned. Derivative names must start with "Llama".
Identifiers
- Hugging Face
- meta-llama/Meta-Llama-3.1-70B-Instruct
- Modality record
- text->text
- Catalogue slug
- meta-llama-llama-3-1-70b-instruct