- 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
- 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
- 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
- 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
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.
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| Q4_K_M4.88 bits per weight, measured median | 39.2 GBestimated | 42.2 GB39.2 + 2.5 + 0.50 | |
| Q5_K_M5.71 bits per weight, measured median | 45.9 GBestimated | 48.9 GB45.9 + 2.5 + 0.50 | |
| Q6_K6.57 bits per weight, measured median | 52.7 GBestimated | 55.7 GB52.7 + 2.5 + 0.50 | |
| Q8_08.50 bits per weight, measured median | 68.3 GBestimated | 71.3 GB68.3 + 2.5 + 0.50 |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| F16original weights | 128.5 GBfile size | 131.5 GB128.5 + 2.5 + 0.50 |
hf download meta-llama/Llama-2-70b-chat-hf --local-dir Llama-2-70b-chat-hfOther conversions (8; sizes not read)
- amd/Llama-2-70b-chat-hf_FP8_MLPerf_V2 FP8, 49 downloads
- amd/Llama-2-70b-chat-hf-WMXFP4-AMXFP4-KVFP8-Scale-UINT8-MLPerf-GPTQ GPTQ, 37 downloads
- mlc-ai/Llama-2-70b-chat-hf-q4f16_1-MLC Other, 28 downloads
- amd/Llama-2-70b-chat-hf-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8 Other, 28 downloads
- espressor/meta-llama.Llama-2-70b-chat-hf_W8A8_FP8 FP8, w8a8, 27 downloads
- lierseleow/Llama-2-70b-chat-hf-bnb-8bit bitsandbytes, 8bit, 14 downloads
- lierseleow/Llama-2-70b-chat-hf-bnb-4bit bitsandbytes, 4bit, 10 downloads
- softmax/Llama-2-70b-chat-hf-marlin GPTQ, 5 downloads
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
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.