{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/the-era-of-1-bit-llms-all-large-language","title":"The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits","arxiv_id":"2402.17764","date":"2024-02-27","proceeding":null,"authors":["Shuming Ma","Hongyu Wang","Lingxiao Ma","Lei Wang","Wenhui Wang","Shaohan Huang","Li Dong","Ruiping Wang","Jilong Xue","Furu Wei"],"abstract":"Recent research, such as BitNet, is paving the way for a new era of 1-bit Large Language Models (LLMs). In this work, we introduce a 1-bit LLM variant, namely BitNet b1.58, in which every single parameter (or weight) of the LLM is ternary {-1, 0, 1}. It matches the full-precision (i.e., FP16 or BF16) Transformer LLM with the same model size and training tokens in terms of both perplexity and end-task performance, while being significantly more cost-effective in terms of latency, memory, throughput, and energy consumption. More profoundly, the 1.58-bit LLM defines a new scaling law and recipe for training new generations of LLMs that are both high-performance and cost-effective. Furthermore, it enables a new computation paradigm and opens the door for designing specific hardware optimized for 1-bit LLMs.","url_abs":"https://arxiv.org/abs/2402.17764v1","url_pdf":"https://arxiv.org/pdf/2402.17764v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"the-era-of-1-bit-llms-all-large-language","repo_url":"https://github.com/Entropy-xcy/bitnet158","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"the-era-of-1-bit-llms-all-large-language","repo_url":"https://github.com/microsoft/bitblas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"the-era-of-1-bit-llms-all-large-language","repo_url":"https://github.com/ramonpeter/hep-bitnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"all","task_name":"All"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.17764","atlas_url":"https://app.syntology.ai/?focus=2402.17764","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17764"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Entropy-xcy/bitnet158","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ramonpeter/hep-bitnet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/bitblas","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran":1},"by_repo_kind":{"listed":{"samples":2,"ran":2,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"2346bd33c6ee4a6a","entry":"absmax_quantize","repo":"Entropy-xcy/bitnet158","repo_kind":"listed","path":"bitnet158/bitlinear158.py","file_url":"https://github.com/Entropy-xcy/bitnet158/blob/HEAD/bitnet158/bitlinear158.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"AFL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"2346bd33c6ee4a6a"}},{"code_sha256_prefix":"bb6778a281ed0015","entry":"get_rasterization_code","repo":"microsoft/bitblas","repo_kind":"listed","path":"bitblas/base/utils.py","file_url":"https://github.com/microsoft/bitblas/blob/HEAD/bitblas/base/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bb6778a281ed0015"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}