Skip to content
Weights Not Walls
Menu

meta-llama

Meta-Llama-3-70B-Instruct

Reviewedgated on the Hub
Size
70.6B parameterscounted from the safetensors header on the Hub
Licence
unknown, Meta Llama 3 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 release date, in which case you need a licence from Meta. If you distribute it or a product using it you must display "Built with Meta Llama 3", models built from it must start their name with "Llama 3", and you may not use it or its outputs to improve any other large language model. The Acceptable Use Policy (a separate document, not in this text) is part of the licence.
On the Hub since
17 Apr 2024the date the repo was created
Context length
Not known
Fine-tune
of meta-llama/Meta-Llama-3-70BLlamaForCausalLM
On Hugging Face
meta-llama/Meta-Llama-3-70B-Instruct53k downloads in the last 30 days, 1.5k likes

Scores

6 independent results on 6 eval sets
GPQA diamondRe-run by Epoch AI
  • default setting40.6%±2.627 Jan 2025, log

Epoch's name: Meta-Llama-3-70B-Instruct. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results

MATH level 5Re-run by Epoch AI
  • default setting22.6%±0.827 Jan 2025, log

Epoch's name: Meta-Llama-3-70B-Instruct. Best closed model on this set: gpt-5-2025-08-07_high, 98.1% (OpenAI). All 108 results

OTIS Mock AIME 2024-2025Re-run by Epoch AI
  • default setting4.3%±2.225 Feb 2025, log

Epoch's name: Meta-Llama-3-70B-Instruct. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 results

CybenchReported

Epoch's name: Meta-Llama-3-70B-Instruct. Best closed model on this set: claude-opus-4-6_unknown, 93.0% (Anthropic). All 22 results

DTBenchReported

Epoch's name: Meta-Llama-3-70B-Instruct. Best closed model on this set: claude-fable-5-2_unknown, 99.2% (Anthropic). All 241 results

MMLUReported

Epoch's name: Meta-Llama-3-70B-Instruct. Best closed model on this set: gpt-4o-2024-11-20, 88.1% (OpenAI). All 217 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

file sizes read from the Hub 19 Nov 2026

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 (MaziyarPanahi/Meta-Llama-3-70B-Instruct-GPTQ), 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

QuantFactory/Meta-Llama-3-70B-Instruct-GGUF (converted by QuantFactory), 1.9k downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
Q3_K_S28.8 GBfile size31.8 GB28.8 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q3_K_S
Ollama
ollama run hf.co/QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q3_K_S
Download
hf download QuantFactory/Meta-Llama-3-70B-Instruct-GGUF --include "Meta-Llama-3-70B-Instruct.Q3_K_S.gguf" --local-dir Meta-Llama-3-70B-Instruct-GGUF
Q3_K_M31.9 GBfile size34.9 GB31.9 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q3_K_M
Ollama
ollama run hf.co/QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q3_K_M
Download
hf download QuantFactory/Meta-Llama-3-70B-Instruct-GGUF --include "Meta-Llama-3-70B-Instruct.Q3_K_M.gguf" --local-dir Meta-Llama-3-70B-Instruct-GGUF
Q3_K_L34.6 GBfile size37.6 GB34.6 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q3_K_L
Ollama
ollama run hf.co/QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q3_K_L
Download
hf download QuantFactory/Meta-Llama-3-70B-Instruct-GGUF --include "Meta-Llama-3-70B-Instruct.Q3_K_L.gguf" --local-dir Meta-Llama-3-70B-Instruct-GGUF
Q4_037.2 GBfile size40.2 GB37.2 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q4_0
Ollama
ollama run hf.co/QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q4_0
Download
hf download QuantFactory/Meta-Llama-3-70B-Instruct-GGUF --include "Meta-Llama-3-70B-Instruct.Q4_0.gguf" --local-dir Meta-Llama-3-70B-Instruct-GGUF
Q4_K_S37.6 GBfile size40.6 GB37.6 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q4_K_S
Ollama
ollama run hf.co/QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q4_K_S
Download
hf download QuantFactory/Meta-Llama-3-70B-Instruct-GGUF --include "Meta-Llama-3-70B-Instruct.Q4_K_S.gguf" --local-dir Meta-Llama-3-70B-Instruct-GGUF
Q4_K_M39.6 GBfile size42.6 GB39.6 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q4_K_M
Ollama
ollama run hf.co/QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q4_K_M
Download
hf download QuantFactory/Meta-Llama-3-70B-Instruct-GGUF --include "Meta-Llama-3-70B-Instruct.Q4_K_M.gguf" --local-dir Meta-Llama-3-70B-Instruct-GGUF
Q4_141.3 GBfile size44.3 GB41.3 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q4_1
Ollama
ollama run hf.co/QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q4_1
Download
hf download QuantFactory/Meta-Llama-3-70B-Instruct-GGUF --include "Meta-Llama-3-70B-Instruct.Q4_1.gguf" --local-dir Meta-Llama-3-70B-Instruct-GGUF
Q5_045.3 GBfile size48.3 GB45.3 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q5_0
Ollama
ollama run hf.co/QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q5_0
Download
hf download QuantFactory/Meta-Llama-3-70B-Instruct-GGUF --include "Meta-Llama-3-70B-Instruct.Q5_0.gguf" --local-dir Meta-Llama-3-70B-Instruct-GGUF
Q5_K_S45.3 GBfile size48.3 GB45.3 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q5_K_S
Ollama
ollama run hf.co/QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q5_K_S
Download
hf download QuantFactory/Meta-Llama-3-70B-Instruct-GGUF --include "Meta-Llama-3-70B-Instruct.Q5_K_S.gguf" --local-dir Meta-Llama-3-70B-Instruct-GGUF
Q5_K_M46.5 GBfile size49.5 GB46.5 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q5_K_M
Ollama
ollama run hf.co/QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q5_K_M
Download
hf download QuantFactory/Meta-Llama-3-70B-Instruct-GGUF --include "Meta-Llama-3-70B-Instruct.Q5_K_M.gguf" --local-dir Meta-Llama-3-70B-Instruct-GGUF
Q5_149.4 GBfile size, 2 parts52.4 GB49.4 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q5_1
Download
hf download QuantFactory/Meta-Llama-3-70B-Instruct-GGUF --include "Meta-Llama-3-70B-Instruct.Q5_1-*-of-00002.gguf" --local-dir Meta-Llama-3-70B-Instruct-GGUF
Q6_K53.9 GBfile size, 2 parts56.9 GB53.9 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q6_K
Download
hf download QuantFactory/Meta-Llama-3-70B-Instruct-GGUF --include "Meta-Llama-3-70B-Instruct.Q6_K-*-of-00002.gguf" --local-dir Meta-Llama-3-70B-Instruct-GGUF
Q8_069.8 GBfile size, 3 parts72.8 GB69.8 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf QuantFactory/Meta-Llama-3-70B-Instruct-GGUF:Q8_0
Download
hf download QuantFactory/Meta-Llama-3-70B-Instruct-GGUF --include "Meta-Llama-3-70B-Instruct.Q8_0-*-of-00003.gguf" --local-dir Meta-Llama-3-70B-Instruct-GGUF

Original weights size from the safetensors header, for vLLM, SGLang, Transformers

FormatSizeMemory neededRepo
BF16original weights131.4 GBfile size134.4 GB131.4 + 2.5 + 0.50
hf download meta-llama/Meta-Llama-3-70B-Instruct --local-dir Meta-Llama-3-70B-Instruct
Other conversions (5; sizes not read)

The Hub tags 47 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.

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.

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.