Skip to content
Weights Not Walls
Menu

meta-llama

Llama-3.3-70B-Instruct

Reviewedgated on the Hub
Size
70.6B parameterscounted from the safetensors header on the Hub
Licence
unknown, Llama 3.3 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 Llama 3.3 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". The Acceptable Use Policy is part of the licence but is a separate document, not in this text.
On the Hub since
26 Nov 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-3.3-70B-Instruct344k downloads in the last 30 days, 3.2k likes

Scores

13 independent results on 12 eval sets
GPQA diamondRe-run by Epoch AI
  • default setting47.4%±2.927 Jan 2025, log

Epoch's name: Llama-3.3-70B-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 setting41.6%±1.227 Jan 2025, log

Epoch's name: Llama-3.3-70B-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 setting5.1%±2.425 Feb 2025, log

Epoch's name: Llama-3.3-70B-Instruct. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 results

BalrogReported

Epoch's name: Llama-3.3-70B-Instruct. Best closed model on this set: gpt-6-astra_max, 68.3% (OpenAI). All 41 results

CritPtReported

Epoch's name: Llama-3.3-70B-Instruct. Best closed model on this set: gemini-4-carbon_high, 36.0% (Google DeepMind). All 271 results

DTBenchReported

Epoch's name: Llama-3.3-70B-Instruct. Best closed model on this set: claude-fable-5-2_unknown, 99.2% (Anthropic). All 241 results

Epoch's name: Llama-3.3-70B-Instruct. Best closed model on this set: gpt-5-2025-08-07_medium, 97.2% (OpenAI). All 61 results

LiveBenchReported

Epoch's name: Llama-3.3-70B-Instruct. Best closed model on this set: gemini-2.5-pro-exp-03-25, 82.3% (Google DeepMind). All 54 results

LMCAReported

Epoch's name: Llama-3.3-70B-Instruct. Best closed model on this set: claude-fable-5-2_xhigh, 70.6% (Anthropic). All 203 results

MMLUReported

Epoch's name: Llama-3.3-70B-Instruct. Best closed model on this set: gpt-4o-2024-11-20, 88.1% (OpenAI). All 217 results

SimpleBenchReported

Epoch's name: Llama-3.3-70B-Instruct. Best closed model on this set: claude-fable-5-2_unknown, 94.9% (Anthropic). All 125 results

WeirdMLReported

Epoch's name: Llama-3.3-70B-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

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 (kosbu/Llama-3.3-70B-Instruct-AWQ), 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

bartowski/Llama-3.3-70B-Instruct-GGUF (converted by bartowski), 219k downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
IQ3_XXS25.6 GBfile size28.6 GB25.6 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:IQ3_XXS
Ollama
ollama run hf.co/bartowski/Llama-3.3-70B-Instruct-GGUF:IQ3_XXS
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-IQ3_XXS.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
IQ3_XS27.3 GBfile size30.3 GB27.3 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:IQ3_XS
Ollama
ollama run hf.co/bartowski/Llama-3.3-70B-Instruct-GGUF:IQ3_XS
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-IQ3_XS.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
Q3_K_S28.8 GBfile size31.8 GB28.8 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q3_K_S
Ollama
ollama run hf.co/bartowski/Llama-3.3-70B-Instruct-GGUF:Q3_K_S
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-Q3_K_S.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
IQ3_M29.7 GBfile size32.7 GB29.7 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:IQ3_M
Ollama
ollama run hf.co/bartowski/Llama-3.3-70B-Instruct-GGUF:IQ3_M
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-IQ3_M.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
Q3_K_M31.9 GBfile size34.9 GB31.9 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q3_K_M
Ollama
ollama run hf.co/bartowski/Llama-3.3-70B-Instruct-GGUF:Q3_K_M
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-Q3_K_M.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
Q3_K_L34.6 GBfile size37.6 GB34.6 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q3_K_L
Ollama
ollama run hf.co/bartowski/Llama-3.3-70B-Instruct-GGUF:Q3_K_L
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-Q3_K_L.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
IQ4_XS35.3 GBfile size38.3 GB35.3 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:IQ4_XS
Ollama
ollama run hf.co/bartowski/Llama-3.3-70B-Instruct-GGUF:IQ4_XS
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-IQ4_XS.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
Q3_K_XL35.4 GBfile size38.4 GB35.4 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q3_K_XL
Ollama
ollama run hf.co/bartowski/Llama-3.3-70B-Instruct-GGUF:Q3_K_XL
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-Q3_K_XL.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
Q4_0_4_437.2 GBfile size40.2 GB37.2 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q4_0_4_4
Ollama
ollama run hf.co/bartowski/Llama-3.3-70B-Instruct-GGUF:Q4_0_4_4
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-Q4_0_4_4.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
Q4_0_4_837.2 GBfile size40.2 GB37.2 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q4_0_4_8
Ollama
ollama run hf.co/bartowski/Llama-3.3-70B-Instruct-GGUF:Q4_0_4_8
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-Q4_0_4_8.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
Q4_0_8_837.2 GBfile size40.2 GB37.2 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q4_0_8_8
Ollama
ollama run hf.co/bartowski/Llama-3.3-70B-Instruct-GGUF:Q4_0_8_8
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-Q4_0_8_8.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
IQ4_NL37.3 GBfile size40.3 GB37.3 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:IQ4_NL
Ollama
ollama run hf.co/bartowski/Llama-3.3-70B-Instruct-GGUF:IQ4_NL
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-IQ4_NL.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
Q4_037.4 GBfile size40.4 GB37.4 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q4_0
Ollama
ollama run hf.co/bartowski/Llama-3.3-70B-Instruct-GGUF:Q4_0
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-Q4_0.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
Q4_K_S37.6 GBfile size40.6 GB37.6 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q4_K_S
Ollama
ollama run hf.co/bartowski/Llama-3.3-70B-Instruct-GGUF:Q4_K_S
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-Q4_K_S.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
Q4_K_M39.6 GBfile size42.6 GB39.6 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q4_K_M
Ollama
ollama run hf.co/bartowski/Llama-3.3-70B-Instruct-GGUF:Q4_K_M
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-Q4_K_M.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
Q4_K_L40.3 GBfile size43.3 GB40.3 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q4_K_L
Ollama
ollama run hf.co/bartowski/Llama-3.3-70B-Instruct-GGUF:Q4_K_L
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-Q4_K_L.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
Q5_K_S45.3 GBfile size48.3 GB45.3 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q5_K_S
Ollama
ollama run hf.co/bartowski/Llama-3.3-70B-Instruct-GGUF:Q5_K_S
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-Q5_K_S.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
Q5_K_M46.5 GBfile size, 2 parts49.5 GB46.5 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q5_K_M
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-Q5_K_M/Llama-3.3-70B-Instruct-Q5_K_M-*-of-00002.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
Q5_K_L47.1 GBfile size, 2 parts50.1 GB47.1 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q5_K_L
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-Q5_K_L/Llama-3.3-70B-Instruct-Q5_K_L-*-of-00002.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
Q6_K53.9 GBfile size, 2 parts56.9 GB53.9 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q6_K
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-Q6_K/Llama-3.3-70B-Instruct-Q6_K-*-of-00002.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
Q6_K_L54.4 GBfile size, 2 parts57.4 GB54.4 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q6_K_L
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-Q6_K_L/Llama-3.3-70B-Instruct-Q6_K_L-*-of-00002.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
Q8_069.8 GBfile size, 2 parts72.8 GB69.8 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q8_0
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-Q8_0/Llama-3.3-70B-Instruct-Q8_0-*-of-00002.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF
F16131.4 GBfile size, 4 parts134.4 GB131.4 + 2.5 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Llama-3.3-70B-Instruct-GGUF:F16
Download
hf download bartowski/Llama-3.3-70B-Instruct-GGUF --include "Llama-3.3-70B-Instruct-f16/Llama-3.3-70B-Instruct-f16-*-of-00004.gguf" --local-dir Llama-3.3-70B-Instruct-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX 4bitmlx-community/Llama-3.3-70B-Instruct-4bit37.0 GBfile size40.0 GB37.0 + 2.5 + 0.50Download page
MLX 8bitmlx-community/Llama-3.3-70B-Instruct-8bit69.8 GBfile size72.8 GB69.8 + 2.5 + 0.50Download page

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/Llama-3.3-70B-Instruct --local-dir Llama-3.3-70B-Instruct
Other conversions (21; sizes not read)

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

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

8 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.

ProviderInOutContextPrecisionTokens/sFirst tokenUptime 24hToolsJSON
DeepInfra$0.10$0.32128kfp8190.5 s99.4%yesyes
novita$0.14$0.4012knot given500.6 s?yesno
Parasail$0.22$0.50128kfp8580.6 s99.9%noyes
AkashML$0.20$0.52128kfp8191.4 s99.6%yesyes
CoreWeave$0.71$0.71125kfp16790.3 s100.0%yesyes
Groq$0.59$0.79128knot given2230.5 s100.0%yesno
Cloudflare$0.29$2.2523kfp8400.9 s99.4%nono
featherless-ai???not given???not givennot 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-3.3-70B-Instruct:deepinfra", "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

from our snapshot of the Hub

Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.

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.