R1 Distill Llama 70B
DeepSeek · released Jan 20, 2025 · deepseek-ai/DeepSeek-R1-Distill-Llama-70B
- Type
- Open weightsMIT License
- Params
- 70.6B
- Context
- 8K
about 6K words of context
Our take
Written Sep 2, 2026R1 Distill Llama is a 70.6-billion-parameter text-only model from DeepSeek with a permissive MIT licence. Its measured reasoning and instruction-following scores are very weak, so it suits budget hosting or local deployment where licence flexibility matters more than accuracy.
Pick this for self-hosted or budget API use where the MIT licence matters — uniform input and output rates make cost predictable. It is a large dense model you can run locally if you have the hardware. Skip it if you need reliable reasoning, strong instruction following, or long-document work beyond 8,192 tokens.
The case for it
- Permissive MIT licence with no attribution or copyleft requirements.
- 70.6 billion dense parameters, a large local-run option.
The case against it
- Near floor-level performance on graduate-level science questions: 2% correct.
- Less than half of instructions followed correctly on the test we track.
- 8,192-token request limit is short for its parameter class, limiting long-document and few-shot use.
How good is it?
EverydayGeneral questions and everyday reasoning
Not yet scored on Arena Text (overall). It is on MMLU-Pro, in 6th of 16 with 47.5.
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 between 3 days and 4 days ago — each listing carries its own date.
- per 1M tokens
- $0.80 in / $0.80 out
- Context served
- 8K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.80 / $0.80checked 3 days ago | 8K | not measured | Unknown | Unknown | Unknown |
| Novita AIbf16Direct and through OpenRouter | $0.80 / $0.80checked 4 days ago directchecked 3 days ago through OpenRouter | 8K7K max reply through OpenRouter | 23 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | Unknown |
Novita AIAcross 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. 0 appear 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 | ✗ | ✗ | ✗ |
| Novita AIbf16Direct 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: 0 of 2 listings say yes, 2 say no.
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 allowsMIT 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
MIT License
Fully permissive: do anything with attribution. No patent grant, unlike Apache-2.0.
Identifiers
- Hugging Face
- deepseek-ai/DeepSeek-R1-Distill-Llama-70B
- Architecture
- Dense
- Takes in, gives back
- Text in, text out
- Catalogue slug
- deepseek-r1-distill-llama-70b