{"as_of":"2026-10-12","license":"CC-BY-4.0","license_url":"https://creativecommons.org/licenses/by/4.0/","cite_as":"The Local Bench (thelocalbench.com), data as of 2026-10-12, CC BY 4.0","source_url":"https://thelocalbench.com","model":{"id":"llama-3.3-70b","name":"Llama 3.3 70B Instruct","org":"Meta","task":"general","hf_repo":"meta-llama/Llama-3.3-70B-Instruct","gguf_repo":"bartowski/Llama-3.3-70B-Instruct-GGUF","license":{"value":"Llama 3.3 Community License","flag":"verified","source":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct/blob/main/LICENSE"},"datasheet":"TLB-M-0009","rev":"2026.10","as_of":"2026-10-12","summary":"The classic 48 GB model. Two used 3090s or a large unified-memory box; bandwidth, not capacity, sets the speed.","arch":{"params_total":{"value":70.55,"flag":"verified","unit":"B","source":"https://huggingface.co/api/models/unsloth/Llama-3.3-70B-Instruct","note":"safetensors.total from the HF API. Read from an ungated mirror of the gated official repo; identical architecture."},"params_active":{"value":70.55,"flag":"verified","unit":"B","source":"https://huggingface.co/api/models/unsloth/Llama-3.3-70B-Instruct","note":"Dense: all parameters active."},"layers":{"value":80,"flag":"verified","source":"https://huggingface.co/unsloth/Llama-3.3-70B-Instruct/blob/main/config.json","note":"Read from an ungated mirror of the gated official repo; identical architecture."},"kv_heads":{"value":8,"flag":"verified","source":"https://huggingface.co/unsloth/Llama-3.3-70B-Instruct/blob/main/config.json","note":"Read from an ungated mirror of the gated official repo; identical architecture."},"q_heads":{"value":64,"flag":"verified","source":"https://huggingface.co/unsloth/Llama-3.3-70B-Instruct/blob/main/config.json","note":"Read from an ungated mirror of the gated official repo; identical architecture."},"head_dim":{"value":128,"flag":"verified","source":"https://huggingface.co/unsloth/Llama-3.3-70B-Instruct/blob/main/config.json","note":"Read from an ungated mirror of the gated official repo; identical architecture."},"hidden_size":{"value":8192,"flag":"verified","source":"https://huggingface.co/unsloth/Llama-3.3-70B-Instruct/blob/main/config.json","note":"Read from an ungated mirror of the gated official repo; identical architecture."},"context":{"value":131072,"flag":"verified","unit":"tokens","source":"https://huggingface.co/unsloth/Llama-3.3-70B-Instruct/blob/main/config.json"}},"quants":{"Q3_K_M":{"bpw":3.91,"file_gb":{"value":34.27,"flag":"verified","unit":"GB","source":"https://huggingface.co/bartowski/Llama-3.3-70B-Instruct-GGUF/tree/main","note":"Sum of GGUF file sizes (Q3_K_M) from the HF API tree listing."},"kld":{"value":0.071,"flag":"sample","note":"Placeholder until KLD runs (brief §4.2)."}},"Q4_K_M":{"bpw":4.85,"file_gb":{"value":42.52,"flag":"verified","unit":"GB","source":"https://huggingface.co/bartowski/Llama-3.3-70B-Instruct-GGUF/tree/main","note":"Sum of GGUF file sizes (Q4_K_M) from the HF API tree listing."},"kld":{"value":0.017,"flag":"sample","note":"Placeholder until KLD runs (brief §4.2)."}},"Q5_K_M":{"bpw":5.69,"file_gb":{"value":49.95,"flag":"verified","unit":"GB","source":"https://huggingface.co/bartowski/Llama-3.3-70B-Instruct-GGUF/tree/main","note":"Sum of GGUF file sizes (Q5_K_M) from the HF API tree listing."},"kld":{"value":0.008,"flag":"sample","note":"Placeholder until KLD runs (brief §4.2)."}},"Q6_K":{"bpw":6.56,"file_gb":{"value":57.89,"flag":"verified","unit":"GB","source":"https://huggingface.co/bartowski/Llama-3.3-70B-Instruct-GGUF/tree/main","note":"Sum of GGUF file sizes (Q6_K) from the HF API tree listing."},"kld":{"value":0.004,"flag":"sample","note":"Placeholder until KLD runs (brief §4.2)."}},"Q8_0":{"bpw":8.5,"file_gb":{"value":74.98,"flag":"verified","unit":"GB","source":"https://huggingface.co/bartowski/Llama-3.3-70B-Instruct-GGUF/tree/main","note":"Sum of GGUF file sizes (Q8_0) from the HF API tree listing."},"kld":{"value":0.001,"flag":"sample","note":"Placeholder until KLD runs (brief §4.2)."}}},"quality":{"arena_text":{"value":1274.2,"flag":"sourced","source":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","note":"LMArena text, overall, entry 'llama-3.3-70b-instruct': 1274.2 (95% CI 1270.8–1277.7, 54,504 votes), leaderboard published 2026-10-08. CC-BY-4.0."}}},"runs":[]}