Skip to content
Weights Not Walls
Menu

meta-llama

Llama-2-70b-chat-hf

Reviewedgated on the Hub
Size
69.0B parameterscounted from the safetensors header on the Hub
Licence
unknown, Llama 2 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 2 release date, in which case you need a licence from Meta. You may not use Llama 2 or its outputs to improve any other large language model, and the Acceptable Use Policy (a separate document, not in this text) is part of the licence. Redistribution needs a copy of the agreement and a Notice file.
On the Hub since
14 Jul 2023the date the repo was created
Context length
Not known
Kind
Base model (no base model declared on the Hub)LlamaForCausalLM
On Hugging Face
meta-llama/Llama-2-70b-chat-hf4.1k downloads in the last 30 days, 2.2k likes

Scores

3 independent results on 3 eval sets
GPQA diamondRe-run by Epoch AI
  • default setting26.3%±2.027 Jan 2025, log

Epoch's name: Llama-2-70b-chat-hf. 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 setting3.3%±0.327 Jan 2025, log

Epoch's name: Llama-2-70b-chat-hf. 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 setting0.0%25 Feb 2025, log

Epoch's name: Llama-2-70b-chat-hf. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 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 (amd/Llama-2-70b-chat-hf_FP8_MLPerf_V2), at 16-bit precision. Choose a machine above to see a verdict for each format. Method

Estimated sizes no measured GGUF files for this model

From the parameter count and the bits per weight of each level (the median measured over the GGUF files in our snapshot, or the format's block size). Real files differ by a few per cent.

FormatSizeMemory neededRepo
Q4_K_M4.88 bits per weight, measured median39.2 GBestimated42.2 GB39.2 + 2.5 + 0.50
Q5_K_M5.71 bits per weight, measured median45.9 GBestimated48.9 GB45.9 + 2.5 + 0.50
Q6_K6.57 bits per weight, measured median52.7 GBestimated55.7 GB52.7 + 2.5 + 0.50
Q8_08.50 bits per weight, measured median68.3 GBestimated71.3 GB68.3 + 2.5 + 0.50

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

FormatSizeMemory neededRepo
F16original weights128.5 GBfile size131.5 GB128.5 + 2.5 + 0.50
hf download meta-llama/Llama-2-70b-chat-hf --local-dir Llama-2-70b-chat-hf
Other conversions (8; sizes not read)

The Hub tags 14 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, 13:56 UTC. The repo. Found a mistake on this page? Tell us.