- Size
- 70.6B parameterscounted from the safetensors header on the Hub
- Licence
- unknown, Llama 3.1 Community License AgreementOur reading, check the licence: Commercial use is allowed unless your products had more than 700 million monthly active users in the calendar month before the Llama 3.1 release date, in which case you need a licence from Meta. If you distribute it, or a product or service containing it, you must include the agreement and display "Built with Llama", and any AI model built with Llama or its outputs must start its name with "Llama" (unlike Llama 3, there is no ban on using outputs to improve other models). The Acceptable Use Policy is part of the licence but is a separate document, not in this text.
- On the Hub since
- 16 Jul 2024the date the repo was created
- Context length
- 128k tokensas an API provider reports it
- Fine-tune
- of meta-llama/Llama-3.1-70BLlamaForCausalLM
- On Hugging Face
- meta-llama/Llama-3.1-70B-Instruct91k downloads in the last 30 days, 1.0k likes
Scores
- default setting44.2%±2.527 Jan 2025, log
Epoch's name: Llama-3.1-70B-Instruct. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results
- default setting36.7%±1.027 Jan 2025, log
Epoch's name: Llama-3.1-70B-Instruct. Best closed model on this set: gpt-5-2025-08-07_high, 98.1% (OpenAI). All 108 results
- default setting3.6%±1.725 Feb 2025, log
Epoch's name: Llama-3.1-70B-Instruct. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 results
- default setting27.9%±1.411 Nov 2024, balrogai.com
Epoch's name: Llama-3.1-70B-Instruct. Best closed model on this set: gpt-6-astra_max, 68.3% (OpenAI). All 41 results
- default setting60.0%conceptualreasoning.ai
Epoch's name: Llama-3.1-70B-Instruct. Best closed model on this set: claude-fable-5-2_unknown, 99.2% (Anthropic). All 241 results
- default setting14.8%9.8 to 19.9conceptualreasoning.ai
Epoch's name: Llama-3.1-70B-Instruct. Best closed model on this set: claude-fable-5-2_xhigh, 70.6% (Anthropic). All 203 results
- Shots: 580.1%Stanford CRFM Leaderboard
Epoch's name: Llama-3.1-70B-Instruct. Best closed model on this set: gpt-4o-2024-11-20, 88.1% (OpenAI). All 217 results
- Environment model: Claude 3.5 Sonnet6.9%17 Dec 2024, TheAgentCompany experiment results github
- Environment model: Claude 3.5 Sonnet1.7%17 Dec 2024, TheAgentCompany experiment results github
Epoch's name: Llama-3.1-70B-Instruct. Best closed model on this set: gemini-2.5-flash-preview-09-2025, 41.1% (Google DeepMind). All 16 results
- default setting9.0%±0.0htihle.github.io
Epoch's name: Llama-3.1-70B-Instruct. Best closed model on this set: gpt-6-astra_promax, 93.6% (OpenAI). All 173 results
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 2.5 GB, worked out from the model's config (RedHatAI/Meta-Llama-3.1-70B-Instruct-FP8), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF (converted by MaziyarPanahi), 40k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ3_XS | 27.3 GBfile size | 30.3 GB27.3 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:IQ3_XSOllama ollama run hf.co/MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:IQ3_XSDownload hf download MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF --include "Meta-Llama-3.1-70B-Instruct.IQ3_XS.gguf" --local-dir Meta-Llama-3.1-70B-Instruct-GGUF |
| Q3_K_S | 28.8 GBfile size | 31.8 GB28.8 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:Q3_K_SOllama ollama run hf.co/MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:Q3_K_SDownload hf download MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF --include "Meta-Llama-3.1-70B-Instruct.Q3_K_S.gguf" --local-dir Meta-Llama-3.1-70B-Instruct-GGUF |
| Q3_K_M | 31.9 GBfile size | 34.9 GB31.9 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:Q3_K_MOllama ollama run hf.co/MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:Q3_K_MDownload hf download MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF --include "Meta-Llama-3.1-70B-Instruct.Q3_K_M.gguf" --local-dir Meta-Llama-3.1-70B-Instruct-GGUF |
| Q3_K_L | 34.6 GBfile size | 37.6 GB34.6 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:Q3_K_LOllama ollama run hf.co/MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:Q3_K_LDownload hf download MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF --include "Meta-Llama-3.1-70B-Instruct.Q3_K_L.gguf" --local-dir Meta-Llama-3.1-70B-Instruct-GGUF |
| IQ4_XS | 35.3 GBfile size | 38.3 GB35.3 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:IQ4_XSOllama ollama run hf.co/MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:IQ4_XSDownload hf download MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF --include "Meta-Llama-3.1-70B-Instruct.IQ4_XS.gguf" --local-dir Meta-Llama-3.1-70B-Instruct-GGUF |
| Q4_K_S | 37.6 GBfile size | 40.6 GB37.6 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:Q4_K_SOllama ollama run hf.co/MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:Q4_K_SDownload hf download MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF --include "Meta-Llama-3.1-70B-Instruct.Q4_K_S.gguf" --local-dir Meta-Llama-3.1-70B-Instruct-GGUF |
| Q4_K_M | 39.6 GBfile size | 42.6 GB39.6 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:Q4_K_MOllama ollama run hf.co/MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:Q4_K_MDownload hf download MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF --include "Meta-Llama-3.1-70B-Instruct.Q4_K_M.gguf" --local-dir Meta-Llama-3.1-70B-Instruct-GGUF |
| Q5_K_S | 45.3 GBfile size | 48.3 GB45.3 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:Q5_K_SOllama ollama run hf.co/MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:Q5_K_SDownload hf download MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF --include "Meta-Llama-3.1-70B-Instruct.Q5_K_S.gguf" --local-dir Meta-Llama-3.1-70B-Instruct-GGUF |
| Q5_K_M | 46.5 GBfile size | 49.5 GB46.5 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:Q5_K_MOllama ollama run hf.co/MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:Q5_K_MDownload hf download MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF --include "Meta-Llama-3.1-70B-Instruct.Q5_K_M.gguf" --local-dir Meta-Llama-3.1-70B-Instruct-GGUF |
| Q6_K | 53.9 GBfile size, 6 parts | 56.9 GB53.9 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF:Q6_KDownload hf download MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF --include "Meta-Llama-3.1-70B-Instruct.Q6_K.gguf-*-of-00006.gguf" --local-dir Meta-Llama-3.1-70B-Instruct-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 5bitbaa-ai/Llama-3.1-70B-Instruct-SWAN-5bit-MLX | 47.2 GBfile size | 50.2 GB47.2 + 2.5 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 131.4 GBfile size | 134.4 GB131.4 + 2.5 + 0.50 |
hf download meta-llama/Llama-3.1-70B-Instruct --local-dir Llama-3.1-70B-InstructOther conversions (22; sizes not read)
- RedHatAI/Meta-Llama-3.1-70B-Instruct-FP8 FP8, 143k downloads
- unsloth/Meta-Llama-3.1-70B-Instruct Other, 4.4k downloads
- RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w4a16 GPTQ, w4a16, 3.5k downloads
- unsloth/Meta-Llama-3.1-70B-Instruct-bnb-4bit bitsandbytes, 4bit, 2.3k downloads
- RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a8 Other, w8a8, 1.3k downloads
- amd/Llama-3.1-70B-Instruct-FP8-KV FP8, 1.1k downloads
- RedHatAI/Meta-Llama-3.1-70B-Instruct-FP8-dynamic FP8, 675 downloads
- mlc-ai/Llama-3.1-70B-Instruct-q3f16_1-MLC Other, 171 downloads
- jy395/Meta-Llama-3.1-70B-Instruct-rtn-w4a16 Other, w4a16, 144 downloads
- RedHatAI/Llama-3.1-70B-Instruct-NVFP4 NVFP4, 75 downloads
- turboderp/Llama-3.1-70B-Instruct-exl3 EXL3, 60 downloads
- jy395/Meta-Llama-3.1-70B-Instruct-gptq-w4a16-c1 GPTQ, w4a16, 55 downloads
- jy395/Meta-Llama-3.1-70B-Instruct-gptq-w4a16-c3 GPTQ, w4a16, 53 downloads
- jy395/Meta-Llama-3.1-70B-Instruct-awq-w4a16-c1 AWQ, w4a16, 51 downloads
- jy395/Meta-Llama-3.1-70B-Instruct-awq-w4a16-c3 AWQ, w4a16, 45 downloads
- yejingfu/nmagic-Meta-Llama-3.1-70B-Instruct-FP8 FP8, 34 downloads
- RedHatAI/Llama-3.1-70B-Instruct-NVFP4A16 NVFP4, 34 downloads
- xmadai/Llama-3.1-70B-Instruct-xMADai-INT4 GPTQ, int4, 28 downloads
- fsaudm/Meta-Llama-3.1-70B-Instruct-NF4 bitsandbytes, 21 downloads
- JongYeop/Llama-3.1-70B-Instruct-NVFP4-W4A4 NVFP4, 20 downloads
- lierseleow/Llama-3.1-70B-Instruct-bnb-4bit bitsandbytes, 4bit, 15 downloads
- fsaudm/Meta-Llama-3.1-70B-Instruct-INT8 bitsandbytes, int8, 14 downloads
The Hub tags 100 or more quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
2 providers serve this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.
| Provider | In | Out | Context | Precision | Tokens/s | First token | Uptime 24h | Tools | JSON |
|---|---|---|---|---|---|---|---|---|---|
| Amazon Bedrock | $0.72 | $0.72 | 128k | not given | 73 | 0.4 s | 100.0% | yes | no |
| featherless-ai | ? | ? | ? | not given | ? | ? | ? | not given | not given |
Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.
curl https://router.huggingface.co/v1/chat/completions \
-H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \
-d '{"model": "meta-llama/Llama-3.1-70B-Instruct:amazon-bedrock", "messages": [{"role": "user", "content": "Hello"}]}'Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Fine-tunes of this model
Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.
- nvidia/Llama-3.1-Nemotron-70B-Instruct-HF70.6B14kReviewed
- nvidia/Llama-3.1-70B-Instruct-FP870.6B3.4kUnreviewed
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.