{"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":"qwen3-8b","name":"Qwen3 8B","org":"Alibaba Qwen","task":"general","hf_repo":"Qwen/Qwen3-8B","gguf_repo":"Qwen/Qwen3-8B-GGUF","license":{"value":"Apache-2.0","flag":"verified","source":"https://www.apache.org/licenses/LICENSE-2.0"},"datasheet":"TLB-M-0002","rev":"2026.10","as_of":"2026-10-12","summary":"A small dense model with switchable thinking. The pick for 8 to 12 GB cards when you want Apache-2.0 terms.","arch":{"params_total":{"value":8.19,"flag":"verified","unit":"B","source":"https://huggingface.co/api/models/Qwen/Qwen3-8B","note":"safetensors.total from the HF API."},"params_active":{"value":8.19,"flag":"verified","unit":"B","source":"https://huggingface.co/api/models/Qwen/Qwen3-8B","note":"Dense: all parameters active."},"layers":{"value":36,"flag":"verified","source":"https://huggingface.co/Qwen/Qwen3-8B/blob/main/config.json"},"kv_heads":{"value":8,"flag":"verified","source":"https://huggingface.co/Qwen/Qwen3-8B/blob/main/config.json"},"q_heads":{"value":32,"flag":"verified","source":"https://huggingface.co/Qwen/Qwen3-8B/blob/main/config.json"},"head_dim":{"value":128,"flag":"verified","source":"https://huggingface.co/Qwen/Qwen3-8B/blob/main/config.json"},"hidden_size":{"value":4096,"flag":"verified","source":"https://huggingface.co/Qwen/Qwen3-8B/blob/main/config.json"},"context":{"value":32768,"flag":"sourced","unit":"tokens","source":"https://huggingface.co/Qwen/Qwen3-8B","note":"config.json lists max_position_embeddings 40,960; the model card gives 32,768 native and 131,072 with YaRN."}},"quants":{"Q3_K_M":{"bpw":3.91,"file_gb":{"value":4,"flag":"estimate","unit":"GB","note":"params_total × 3.91 bpw ÷ 8 (brief §7.3 fallback); no GGUF of this quant in Qwen/Qwen3-8B-GGUF."},"kld":{"value":0.071,"flag":"sample","note":"Placeholder until KLD runs (brief §4.2)."}},"Q4_K_M":{"bpw":4.85,"file_gb":{"value":5.03,"flag":"verified","unit":"GB","source":"https://huggingface.co/Qwen/Qwen3-8B-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":5.85,"flag":"verified","unit":"GB","source":"https://huggingface.co/Qwen/Qwen3-8B-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":6.73,"flag":"verified","unit":"GB","source":"https://huggingface.co/Qwen/Qwen3-8B-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":8.71,"flag":"verified","unit":"GB","source":"https://huggingface.co/Qwen/Qwen3-8B-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)."}},"F16":{"bpw":16,"file_gb":{"value":16.38,"flag":"estimate","unit":"GB","note":"params_total × 16.0 bpw ÷ 8 (brief §7.3 fallback); no GGUF of this quant in Qwen/Qwen3-8B-GGUF."}}},"quality":{"arena_text":{"value":1270,"flag":"sample","note":"Placeholder: this model has no entry in the LMArena text leaderboard dataset (checked 2026-10-12). Not a real score."}}},"runs":[]}