Up to date
meta-llama Llama 2 Community License out 3 years ago
69.0B parameters, text in, text out.
Verified 2026-10-25 Rank #228 in LLMs · score 87.4 method v1 Sources 3 Downloads 30d 3.9k · #556 of 619 tracked
Picked by rule from 37 tracked pieces: the lab's own post, the most shared, a field report, the latest.
Fine-tuning open-source Llama 2 models can replace GPT-3.5 and GPT-4 for specific tasks, with a fine-tuned Llama 7B matching GPT-4 labels 95% of the time on a test set.
Ollama enables local execution of uncensored Llama 2 variants, such as the 7B model fine-tuned using Wizard-Vicuna conversation dataset and Nous Hermes Llama 2 13B fine-tuned on over 300,000 instructions.
The 2 picks above, plus these 23. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
No API provider serves it, so its downloads are people running it themselves: 14 quantized builds and 100 Spaces.
Top Spaces running it: ysharma/Explore_llamav2_with_TGI ♥ 1,203 · h2oai/h2ogpt-chatbot ♥ 295 · allenai/WildBench ♥ 232 · h2oai/h2ogpt-chatbot2 ♥ 167
Weights only, an estimate: leave room for the KV cache. Method
About 41 GB at INT4, 83 GB at FP8, 166 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2023-07-14), amber triangles are 10 dated articles (each links to it).
35 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Everything else, folded: the full tables, every source.
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
Listed in LLMs
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | LlamaForCausalLM |
| Model type | llama |
| Params by dtype | F32: 5,120 · F16: 68,976,648,192 |
| Size band | XL |
| MoE | no |
| Gated | manual |
| Papers | arXiv:2307.09288 |
| License | Llama 2 Community License (llama2) |
| Hub snapshot | 2026-10-25 |
vLLM: supported · LlamaForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · LlamaForCausalLM · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
Weights-only memory for Llama-2-70b-chat-hf: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 166 GB · Multi-GPU node (<640 GB) |
|---|---|
| FP8 (1 byte/param) | 83 GB · Multi-GPU node (<640 GB) |
| INT4 (0.5 bytes/param) | 41 GB · Single high-end GPU (<80 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
quantized: 14finetune: 6adapter: 15
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:36 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:04 UTC · Last verified 2026-10-25
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
