Up to date
meta-llama Llama 2 Community License out 3 years ago
6.74B parameters, text in, text out.
Verified 2026-10-25 Rank #114 in LLMs · score 97.4 method v1 Sources 3 Downloads 30d 435.6k · #174 of 619 tracked
Picked by rule from 38 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: 78 quantized builds and 100 Spaces.
Top Spaces running it: pliny-the-prompter/obliteratus ♥ 621 · tomg-group-umd/lm-watermarking ♥ 100 · Illia56/Ask-AI-Youtube ♥ 81 · Norod78/OpenELM_3B_Demo ♥ 59
Weights only, an estimate: leave room for the KV cache. Method
About 4.0 GB at INT4, 8.1 GB at FP8, 16 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 (2023-07-13), amber triangles are 10 dated articles (each links to it).
3,534 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: 2,048 · F16: 6,738,415,616 |
| Size band | M |
| 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-2-7b-hf: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 16 GB · Single GPU (<24 GB) |
|---|---|
| FP8 (1 byte/param) | 8.1 GB · Single GPU (<24 GB) |
| INT4 (0.5 bytes/param) | 4.0 GB · Single GPU (<24 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
quantized: 78finetune: 990adapter: 2,455merge: 11
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| TheBloke/Llama-2-7B-GPTQ | quantized | GPTQ | 6.74B | M | llama2 | TheBloke | 81 | 1.8M |
| TheBloke/Llama-2-7B-GGUF | quantized | GGUF | — | — | llama2 | TheBloke | 207 | 625.3k |
| allenai/tulu-2-7b | finetune | — | — | — | — | allenai | 11 | 151.8k |
| allenai/tulu-2-dpo-7b | finetune | — | — | — | other | allenai | 21 | 118.8k |
| Styxxxx/llama2_7b_lora-common_gen | adapter | — | — | — | — | Styxxxx | 0 | 100.8k |
| Styxxxx/llama2_7b_lora-multirc | adapter | — | — | — | — | Styxxxx | 0 | 99.9k |
| Styxxxx/llama2_7b_lora-arc_challenge | adapter | — | — | — | — | Styxxxx | 0 | 97.9k |
| Styxxxx/llama2_7b_lora-arc_easy | adapter | — | — | — | — | Styxxxx | 0 | 91.8k |
| rinna/youri-7b | finetune | — | 6.74B | M | llama2 | rinna | 21 | 89.1k |
| Styxxxx/llama2_7b_lora-cosmos_qa | adapter | — | — | — | — | Styxxxx | 0 | 89.2k |
| Styxxxx/llama2_7b_lora-copa | adapter | — | — | — | — | Styxxxx | 0 | 84.4k |
| TheBloke/Llama-2-7B-AWQ | quantized | AWQ | 6.74B | M | llama2 | TheBloke | 17 | 79.3k |
| Styxxxx/llama2_7b_lora-dart | adapter | — | — | — | — | Styxxxx | 0 | 79.6k |
| Styxxxx/llama2_7b_lora-anli_r1 | adapter | — | — | — | — | Styxxxx | 0 | 78.2k |
| Styxxxx/llama2_7b_lora-natural_questions | adapter | — | — | — | — | Styxxxx | 0 | 77k |
| Styxxxx/llama2_7b_lora-openbookqa | adapter | — | — | — | — | Styxxxx | 0 | 74.2k |
| Styxxxx/llama2_7b_lora-glue_mrpc | adapter | — | — | — | — | Styxxxx | 0 | 68.4k |
| Styxxxx/llama2_7b_lora-wmt16_translate_deen | adapter | — | — | — | — | Styxxxx | 0 | 64.2k |
| Styxxxx/llama2_7b_lora-wmt16_translate_csen | adapter | — | — | — | — | Styxxxx | 0 | 62.4k |
| RedHatAI/Llama-2-7b-gsm8k | finetune | — | — | — | — | RedHatAI | 5 | 61.9k |
| Styxxxx/llama2_7b_lora-web_nlg_en | adapter | — | — | — | — | Styxxxx | 0 | 61.7k |
| Styxxxx/llama2_7b_lora-drop | adapter | — | — | — | — | Styxxxx | 0 | 56k |
| diffusionfamily/diffullama | finetune | — | 6.74B | M | apache-2.0 | diffusionfamily | 14 | 53.3k |
| Styxxxx/llama2_7b_lora-sst2 | adapter | — | — | — | — | Styxxxx | 0 | 53.4k |
| Styxxxx/llama2_7b_lora-anli_r2 | adapter | — | — | — | — | Styxxxx | 0 | 52.9k |
| Styxxxx/llama2_7b_lora-wmt16_translate_fien | adapter | — | — | — | — | Styxxxx | 0 | 52.9k |
| Styxxxx/llama2_7b_lora-yelp_polarity_reviews | adapter | — | — | — | — | Styxxxx | 0 | 52.4k |
| swapnilbp/llama_tweet_ptune | adapter | — | — | — | — | swapnilbp | 0 | 49.3k |
| Styxxxx/llama2_7b_lora-bool_q | adapter | — | — | — | — | Styxxxx | 0 | 49.2k |
| Styxxxx/llama2_7b_lora-trivia_qa | adapter | — | — | — | — | Styxxxx | 0 | 48.1k |
| Styxxxx/llama2_7b_lora-definite_pronoun_resolution | adapter | — | — | — | — | Styxxxx | 1 | 47.7k |
| Styxxxx/llama2_7b_lora-glue_qqp | adapter | — | — | — | — | Styxxxx | 0 | 47.1k |
| Styxxxx/llama2_7b_lora-record | adapter | — | — | — | — | Styxxxx | 0 | 47k |
| Styxxxx/llama2_7b_lora-wnli | adapter | — | — | — | — | Styxxxx | 0 | 46.3k |
| Styxxxx/llama2_7b_lora-story_cloze | adapter | — | — | — | — | Styxxxx | 0 | 45.5k |
| Styxxxx/llama2_7b_lora-paws_wiki | adapter | — | — | — | — | Styxxxx | 0 | 44.5k |
| Styxxxx/llama2_7b_lora-mnli_matched | adapter | — | — | — | — | Styxxxx | 0 | 43.3k |
| Styxxxx/llama2_7b_lora-mnli_mismatched | adapter | — | — | — | — | Styxxxx | 0 | 42.8k |
| Styxxxx/llama2_7b_lora-anli_r3 | adapter | — | — | — | — | Styxxxx | 0 | 41k |
| Styxxxx/llama2_7b_lora-qnli | adapter | — | — | — | — | Styxxxx | 0 | 40.2k |
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 21:33 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:00 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.
