{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/how-good-are-low-bit-quantized-llama3-models","title":"An empirical study of LLaMA3 quantization: from LLMs to MLLMs","arxiv_id":"2404.14047","date":"2024-04-22","proceeding":null,"authors":["Wei Huang","Xingyu Zheng","Xudong Ma","Haotong Qin","Chengtao Lv","Hong Chen","Jie Luo","Xiaojuan Qi","Xianglong Liu","Michele Magno"],"abstract":"The LLaMA family, a collection of foundation language models ranging from 7B to 65B parameters, has become one of the most powerful open-source large language models (LLMs) and the popular LLM backbone of multi-modal large language models (MLLMs), widely used in computer vision and natural language understanding tasks. In particular, LLaMA3 models have recently been released and have achieved impressive performance in various domains with super-large scale pre-training on over 15T tokens of data. Given the wide application of low-bit quantization for LLMs in resource-constrained scenarios, we explore LLaMA3's capabilities when quantized to low bit-width. This exploration can potentially provide new insights and challenges for the low-bit quantization of LLaMA3 and other future LLMs, especially in addressing performance degradation issues that suffer in LLM compression. Specifically, we comprehensively evaluate the 10 existing post-training quantization and LoRA fine-tuning (LoRA-FT) methods of LLaMA3 on 1-8 bits and various datasets to reveal the low-bit quantization performance of LLaMA3. To uncover the capabilities of low-bit quantized MLLM, we assessed the performance of the LLaMA3-based LLaVA-Next-8B model under 2-4 ultra-low bits with post-training quantization methods. Our experimental results indicate that LLaMA3 still suffers from non-negligible degradation in linguistic and visual contexts, particularly under ultra-low bit widths. This highlights the significant performance gap at low bit-width that needs to be addressed in future developments. We expect that this empirical study will prove valuable in advancing future models, driving LLMs and MLLMs to achieve higher accuracy at lower bit to enhance practicality. Our project is released on https://github.com/Macaronlin/LLaMA3-Quantization , and quantized models are released at https://huggingface.co/Efficient-ML .","url_abs":"https://arxiv.org/abs/2404.14047v3","url_pdf":"https://arxiv.org/pdf/2404.14047v3.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":"how-good-are-low-bit-quantized-llama3-models","repo_url":"https://github.com/macaronlin/llama3-quantization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"how-good-are-low-bit-quantized-llama3-models","repo_url":"https://github.com/MS-P3/code5/tree/main/llama3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[{"method_slug":"llama","method_name":"LLaMA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.14047","atlas_url":"https://app.syntology.ai/?focus=2404.14047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14047"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2404.14047"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2404.14047"},"call":"get_harvested_code_for_paper(arxiv_id=\"2404.14047\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2404.14047"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2404.14047\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2404.14047"},"call":"get_concepts_for_paper(arxiv_id=\"2404.14047\")"}],"by_repo":[{"repo":"macaronlin/llama3-quantization","kind":"official","samples":10,"ran":7,"instrument":4,"unverified":3},{"repo":"MS-P3/code5","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2405.18386"],"harvested_for_calls":[{"arxiv_id":"2405.18386","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2405.18386"},"call":"get_harvested_code_for_paper(arxiv_id=\"2405.18386\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2404.14047.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2404.14047.svg"},"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/MS-P3/code5/tree/main/llama3","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/macaronlin/llama3-quantization","reach":{"status":"ok"}}],"summary":{"ran":2,"ran_draft_wrong":4,"ran_violates":1,"unverified":3},"n_samples":10,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":3,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":10,"ran":7,"n_ran_checked":3,"n_instrument":4,"repositories":1}},"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":10,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":7,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"904cd61df2fe8fb9","code_sha256_prefix":"904cd61df2fe8fb9","entry":"find_layers","repo":"macaronlin/llama3-quantization","repo_kind":"official","path":"models/models_utils.py","file_url":"https://github.com/macaronlin/llama3-quantization/blob/HEAD/models/models_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"module:callable/0/?, layers:list/1/callable, name:str/0/str","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/find-layers","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, macaronlin/llama3-quantization when it was checked","mcp_get_code":{"code_sha256":"904cd61df2fe8fb9"}},{"code_sha256":"2c201f017173954b","code_sha256_prefix":"2c201f017173954b","entry":"get_llama","repo":"macaronlin/llama3-quantization","repo_kind":"official","path":"llama.py","file_url":"https://github.com/macaronlin/llama3-quantization/blob/HEAD/llama.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"model:str/0/str","fixture_out_type":"MockLlamaForCausalLM","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/get-llama","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, macaronlin/llama3-quantization when it was checked","mcp_get_code":{"code_sha256":"2c201f017173954b"}},{"code_sha256":"4df9168e0a0c38eb","code_sha256_prefix":"4df9168e0a0c38eb","entry":"make_disjoint_window","repo":"macaronlin/llama3-quantization","repo_kind":"official","path":"models/models_utils.py","file_url":"https://github.com/macaronlin/llama3-quantization/blob/HEAD/models/models_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"pair:tuple/1/list","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/make-disjoint-window","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, macaronlin/llama3-quantization when it was checked","mcp_get_code":{"code_sha256":"4df9168e0a0c38eb"}},{"code_sha256":"6d5acfb0087d1ee7","code_sha256_prefix":"6d5acfb0087d1ee7","entry":"prod","repo":"macaronlin/llama3-quantization","repo_kind":"official","path":"irqlora.py","file_url":"https://github.com/macaronlin/llama3-quantization/blob/HEAD/irqlora.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"signature":"iterable:list/1/int","fixture_out_type":"int","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"6d5acfb0087d1ee7"},"code_page":"/code/prod","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, macaronlin/llama3-quantization when it was checked","mcp_get_code":{"code_sha256":"6d5acfb0087d1ee7"}},{"code_sha256":"632792cb21b226ee","code_sha256_prefix":"632792cb21b226ee","entry":"quantize_tensor","repo":"macaronlin/llama3-quantization","repo_kind":"official","path":"irqlora.py","file_url":"https://github.com/macaronlin/llama3-quantization/blob/HEAD/irqlora.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"X:Tensor/2/float, L:Tensor/1/float, idx:bool/0/bool","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/quantize-tensor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, macaronlin/llama3-quantization when it was checked","mcp_get_code":{"code_sha256":"632792cb21b226ee"}},{"code_sha256":"94587954e392b665","code_sha256_prefix":"94587954e392b665","entry":"truncate_number","repo":"macaronlin/llama3-quantization","repo_kind":"official","path":"models/transformation.py","file_url":"https://github.com/macaronlin/llama3-quantization/blob/HEAD/models/transformation.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"number:Tensor/2/float, threshold:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"94587954e392b665"},"code_page":"/code/truncate-number","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, macaronlin/llama3-quantization when it was checked","mcp_get_code":{"code_sha256":"94587954e392b665"}},{"code_sha256":"4e53fbbdfa160f7d","code_sha256_prefix":"4e53fbbdfa160f7d","entry":"truncate_number","repo":"macaronlin/llama3-quantization","repo_kind":"official","path":"models/models_utils.py","file_url":"https://github.com/macaronlin/llama3-quantization/blob/HEAD/models/models_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"number:Tensor/2/float, threshold:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"4e53fbbdfa160f7d"},"code_page":"/code/truncate-number","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, macaronlin/llama3-quantization when it was checked","mcp_get_code":{"code_sha256":"4e53fbbdfa160f7d"}},{"code_sha256":"3b51341ed1a0b73e","code_sha256_prefix":"3b51341ed1a0b73e","entry":"get_pile","repo":"macaronlin/llama3-quantization","repo_kind":"official","path":"datautils.py","file_url":"https://github.com/macaronlin/llama3-quantization/blob/HEAD/datautils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-pile","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, macaronlin/llama3-quantization when it was checked","mcp_get_code":{"code_sha256":"3b51341ed1a0b73e"}},{"code_sha256":"bd4f416e271c2fb5","code_sha256_prefix":"bd4f416e271c2fb5","entry":"get_ptb","repo":"macaronlin/llama3-quantization","repo_kind":"official","path":"datautils.py","file_url":"https://github.com/macaronlin/llama3-quantization/blob/HEAD/datautils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-ptb","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, macaronlin/llama3-quantization when it was checked","mcp_get_code":{"code_sha256":"bd4f416e271c2fb5"}},{"code_sha256":"406294899f965c2f","code_sha256_prefix":"406294899f965c2f","entry":"get_wikitext2","repo":"macaronlin/llama3-quantization","repo_kind":"official","path":"datautils.py","file_url":"https://github.com/macaronlin/llama3-quantization/blob/HEAD/datautils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-wikitext2","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, macaronlin/llama3-quantization when it was checked","mcp_get_code":{"code_sha256":"406294899f965c2f"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"ae39c7dbce8aa10c3bdb1bfd7db02955a9d95a2f70d8b0a36e652e318461e0ba","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}