- Size
- 8.0B 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
- Kind
- Base model (no base model declared on the Hub)LlamaForCausalLM
- On Hugging Face
- meta-llama/Meta-Llama-3-8B-Instruct423k downloads in the last 30 days, 6.3k likes
Scores
- default setting26.1%±1.727 Jan 2025, log
Epoch's name: Meta-Llama-3-8B-Instruct. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results
- default setting6.1%±0.427 Jan 2025, log
Epoch's name: Meta-Llama-3-8B-Instruct. Best closed model on this set: gpt-5-2025-08-07_high, 98.1% (OpenAI). All 108 results
- default setting1.9%±1.030 Aug 2026, log
Epoch's name: Meta-Llama-3-8B-Instruct. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 results
- default setting57.3%Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Epoch's name: Meta-Llama-3-8B-Instruct. Best closed model on this set: gpt-3.5-turbo-1106, 58.1% (OpenAI). All 15 results
Epoch's name: Meta-Llama-3-8B-Instruct. Best closed model on this set: gpt-3.5-turbo-1106, 87.4% (OpenAI). All 134 results
- default setting43.9%conceptualreasoning.ai
Epoch's name: Meta-Llama-3-8B-Instruct. Best closed model on this set: claude-fable-5-2_unknown, 99.2% (Anthropic). All 241 results
- Shots: 568.8%Stanford CRFM Leaderboard
- Shots: 566.5%Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Epoch's name: Meta-Llama-3-8B-Instruct. Best closed model on this set: gpt-4o-2024-11-20, 88.1% (OpenAI). All 217 results
- Shots: 1082.6%Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- Shots: 045.0%The Llama 3 Herd of Models
Epoch's name: Meta-Llama-3-8B-Instruct. Best closed model on this set: gpt-3.5-turbo-1106, 86.0% (OpenAI). All 70 results
Epoch's name: Meta-Llama-3-8B-Instruct. Best closed model on this set: claude-2.0, 87.5% (Anthropic). All 115 results
Epoch's name: Meta-Llama-3-8B-Instruct. Best closed model on this set: claude-3-opus-20240229, 88.5% (Anthropic). All 137 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: 1.0 GB, worked out from the model's config (RedHatAI/Meta-Llama-3-8B-Instruct-FP8-KV), 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-3-8B-Instruct-GGUF (converted by MaziyarPanahi), 62k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ3_XS | 3.3 GBfile size | 4.8 GB3.3 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:IQ3_XSOllama ollama run hf.co/MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:IQ3_XSDownload hf download MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF --include "Meta-Llama-3-8B-Instruct.IQ3_XS.gguf" --local-dir Meta-Llama-3-8B-Instruct-GGUF |
| Q3_K_S | 3.4 GBfile size | 4.9 GB3.4 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:Q3_K_SOllama ollama run hf.co/MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:Q3_K_SDownload hf download MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF --include "Meta-Llama-3-8B-Instruct.Q3_K_S.gguf" --local-dir Meta-Llama-3-8B-Instruct-GGUF |
| Q3_K_M | 3.7 GBfile size | 5.2 GB3.7 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:Q3_K_MOllama ollama run hf.co/MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:Q3_K_MDownload hf download MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF --include "Meta-Llama-3-8B-Instruct.Q3_K_M.gguf" --local-dir Meta-Llama-3-8B-Instruct-GGUF |
| Q3_K_L | 4.0 GBfile size | 5.5 GB4.0 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:Q3_K_LOllama ollama run hf.co/MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:Q3_K_LDownload hf download MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF --include "Meta-Llama-3-8B-Instruct.Q3_K_L.gguf" --local-dir Meta-Llama-3-8B-Instruct-GGUF |
| IQ4_XS | 4.1 GBfile size | 5.6 GB4.1 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:IQ4_XSOllama ollama run hf.co/MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:IQ4_XSDownload hf download MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF --include "Meta-Llama-3-8B-Instruct.IQ4_XS.gguf" --local-dir Meta-Llama-3-8B-Instruct-GGUF |
| Q4_K_S | 4.4 GBfile size | 5.9 GB4.4 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:Q4_K_SOllama ollama run hf.co/MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:Q4_K_SDownload hf download MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF --include "Meta-Llama-3-8B-Instruct.Q4_K_S.gguf" --local-dir Meta-Llama-3-8B-Instruct-GGUF |
| Q4_K_M | 4.6 GBfile size | 6.1 GB4.6 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:Q4_K_MOllama ollama run hf.co/MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:Q4_K_MDownload hf download MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF --include "Meta-Llama-3-8B-Instruct.Q4_K_M.gguf" --local-dir Meta-Llama-3-8B-Instruct-GGUF |
| Q5_K_S | 5.2 GBfile size | 6.7 GB5.2 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:Q5_K_SOllama ollama run hf.co/MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:Q5_K_SDownload hf download MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF --include "Meta-Llama-3-8B-Instruct.Q5_K_S.gguf" --local-dir Meta-Llama-3-8B-Instruct-GGUF |
| Q5_K_M | 5.3 GBfile size | 6.8 GB5.3 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:Q5_K_MOllama ollama run hf.co/MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:Q5_K_MDownload hf download MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF --include "Meta-Llama-3-8B-Instruct.Q5_K_M.gguf" --local-dir Meta-Llama-3-8B-Instruct-GGUF |
| Q6_K | 6.1 GBfile size | 7.6 GB6.1 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:Q6_KOllama ollama run hf.co/MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:Q6_KDownload hf download MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF --include "Meta-Llama-3-8B-Instruct.Q6_K.gguf" --local-dir Meta-Llama-3-8B-Instruct-GGUF |
| Q8_0 | 8.0 GBfile size | 9.5 GB8.0 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:Q8_0Ollama ollama run hf.co/MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:Q8_0Download hf download MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF --include "Meta-Llama-3-8B-Instruct.Q8_0.gguf" --local-dir Meta-Llama-3-8B-Instruct-GGUF |
| F16 | 15.0 GBfile size | 16.5 GB15.0 + 1.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:F16Ollama ollama run hf.co/MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF:F16Download hf download MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF --include "Meta-Llama-3-8B-Instruct.fp16.gguf" --local-dir Meta-Llama-3-8B-Instruct-GGUF |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 15.0 GBfile size | 16.5 GB15.0 + 1.0 + 0.50 |
hf download meta-llama/Meta-Llama-3-8B-Instruct --local-dir Meta-Llama-3-8B-InstructOther conversions (7; sizes not read)
- RedHatAI/Meta-Llama-3-8B-Instruct-FP8-KV FP8, 1.3k downloads
- taobao-mnn/Meta-Llama-3-8B-Instruct-MNN Other, 185 downloads
- FriendliAI/Meta-Llama-3-8B-Instruct-fp8 FP8, 113 downloads
- MaziyarPanahi/Meta-Llama-3-8B-Instruct-GPTQ GPTQ, 95 downloads
- Hyun9junn/Meta-Llama-3-8B-Instruct-W4A4KV4-FlatQuant Other, 41 downloads
- espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_int8 Other, w8a8, 37 downloads
- espressor/meta-llama.Meta-Llama-3-8B-Instruct_W4A16 Other, w4a16, 31 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
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.
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.
- mozilla-ai/Meta-Llama-3-8B-Instruct-llamafile19kUnreviewed
- shenzhi-wang/Llama3-8B-Chinese-Chat8.0B9.5kUnreviewed
- lightblue/suzume-llama-3-8B-multilingual8.0B9.4kUnreviewed
- princeton-nlp/Llama-3-8B-ProLong-64k-Base8.0B9.4kUnreviewed
- allenai/intent-aware-lfqa-llama3-8b-intent-explicit2.2kUnreviewed
- allenai/intent-aware-lfqa-llama3-8b-intent-implicit175Unreviewed
- allenai/intent-aware-lfqa-llama3-8b-baseline163Unreviewed
- allenai/intent-aware-lfqa-llama3-8b-multiview163Unreviewed
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.