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 Aug 3, 2026R1 Distill Llama is a 70.6-billion-parameter text model from DeepSeek whose weights can be downloaded under a permissive MIT licence. It inherits reasoning patterns from a larger teacher model and is positioned as a budget inference option, though its benchmark coverage is thin and its scores are modest.
Pick this when you need a permissive licence that allows commercial use and modification, or when low flat-rate inference pricing matters more than top-tier accuracy. It suits lightweight reasoning tasks where the style of thinking is more important than the score. Skip it if you need graduate-level science reasoning, reliable instruction following, or a context window above eight thousand tokens.
The case for it
- Permissive MIT licence with no commercial restrictions, allowing modification and redistribution.
- Low and flat token pricing across providers, with no premium charged for output tokens.
The case against it
- Extremely weak on graduate-level reasoning, with a near-floor score on the GPQA Diamond benchmark.
- Modest instruction-following and broad-knowledge scores, both below typical thresholds for reliable deployment.
- Narrow context window for a model of this size, with no larger variant disclosed and a thin, duplicated benchmark record.
How good is it?
IntelligencePuzzles, maths, exam questions
R1 Distill Llama 70B is not on Arena Text (overall), which is where the rating would come from, so there is no rating here. It is on MMLU-Pro, in 6th of 16 with 41.6.
CodingWriting and fixing code on its own
Nobody we watch has scored R1 Distill Llama 70B for this. We would take the rating from Arena Coding.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored R1 Distill Llama 70B for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Nobody we watch has scored this model for writing. 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.
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.
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 3 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
- $0.80 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 |
|---|---|---|---|---|---|---|
| OpenRouter | $0.80 / $0.80 | 8K | not measured | Unknown | Unknown | Unknown |
| Novita AI | $0.80 / $0.80 | 8K | not measured | Unknown | Unknown | Unknown |
| Novita AIbf16 | $0.80 / $0.80 | 8K | 20 tok/s | No | No | Confirmed |
Novita AIAcross the 3 listings we hold: 1 say they do not train on prompts, 0 say they do and 2 do not say. 1 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 | ✗ | ✗ | ✗ |
| Novita AI | |||
| Novita AIbf16 | ✗ | ✗ | ✗ |
Tool calling: 0 of 3 listings say yes, 2 say no, 1 publishes no parameter list. JSON output: 0 of 3 listings say yes, 2 say no, 1 publishes no parameter list. Strict schema: 0 of 3 listings say yes, 2 say no, 1 publishes no parameter list.
When we formed this view
Dates behind this page
Prices last checked 6h 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.
- 1 of 3 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 3 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 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
- Modality record
- text->text
- Catalogue slug
- deepseek-r1-distill-llama-70b