{
  "label": "GLM-5.3-Flash UD-Q3_K_XL (147.5 GB) reasoning HIGH",
  "tests": {},
  "vision": {},
  "error": "llama-server exited during load:\n0.00.040.806 I srv          init: The UI is disabled\n0.00.040.807 I srv          init: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable\n0.00.040.874 W srv  llama_server: -----------------\n0.00.040.875 W srv  llama_server: CORS is set to allow all origins ('*') and no API key is set\n0.00.040.875 W srv  llama_server: this can be a security risk (cross-origin attacks)\n0.00.040.876 W srv  llama_server: more info: https://github.com/ggml-org/llama.cpp/pull/25655\n0.00.040.876 W srv  llama_server: -----------------\n0.00.042.090 I srv    load_model: loading model '~/.cache/huggingface/hub/models--unsloth--GLM-5.3-Flash-GGUF/snapshots/2975ab414d30340466d8c51533c6e91f0cca64c1/UD-Q3_K_XL/GLM-5.3-Flash-UD-Q3_K_XL-00001-of-00004.gguf'\n0.00.402.765 W common_fit_params: failed to fit params to free device memory: n_gpu_layers already set by user to 999, abort\n0.00.553.229 W load: special_eot_id is not in special_eog_ids - the tokenizer config may be incorrect\n0.00.553.233 W load: special_eom_id is not in special_eog_ids - the tokenizer config may be incorrect\n0.00.580.788 W model has unused tensor blk.45.attn_norm.weight (size = 16384 bytes) -- ignoring\n0.00.580.791 W model has unused tensor blk.45.ffn_norm.weight (size = 16384 bytes) -- ignoring\n0.00.580.793 W model has unused tensor blk.45.attn_q_a.weight (size = 6684672 bytes) -- ignoring\n0.00.580.794 W model has unused tensor blk.45.attn_q_a_norm.weight (size = 6144 bytes) -- ignoring\n0.00.580.796 W model has unused tensor blk.45.attn_q_b.weight (size = 26738688 bytes) -- ignoring\n0.00.580.798 W model has unused tensor blk.45.attn_kv_a_mqa.weight (size = 2228224 bytes) -- ignoring\n0.00.580.799 W model has unused tensor blk.45.attn_kv_a_norm.weight (size = 2048 bytes) -- ignoring\n0.00.580.801 W model has unused tensor blk.45.attn_k_b.weight (size = 8912896 bytes) -- ignoring\n0.00.580.802 W model has unused tensor blk.45.attn_v_b.weight (size = 8912896 bytes) -- ignoring\n0.00.580.804 W model has unused tensor blk.45.attn_output.weight (size = 71303168 bytes) -- ignoring\n0.00.580.805 W model has unused tensor blk.45.indexer.k_norm.weight (size = 512 bytes) -- ignoring\n0.00.580.807 W model has unused tensor blk.45.indexer.k_norm.bias (size = 512 bytes) -- ignoring\n0.00.580.809 W model has unused tensor blk.45.indexer.proj.weight (size = 524288 bytes) -- ignoring\n0.00.580.811 W model has unused tensor blk.45.indexer.attn_k.weight (size = 557056 bytes) -- ignoring\n0.00.580.813 W model has unused tensor blk.45.indexer.attn_q_b.weight (size = 6684672 bytes) -- ignoring\n0.00.580.815 W model has unused tensor blk.45.indexer_compressor_gate.weight (size = 557056 bytes) -- ignoring\n0.00.580.817 W model has unused tensor blk.45.indexer_compressor_ape.weight (size = 2048 bytes) -- ignoring\n0.00.580.819 W model has unused tensor blk.45.ffn_gate_inp.weight (size = 4718592 bytes) -- ignoring\n0.00.580.820 W model has unused tensor blk.45.exp_probs_b.bias (size = 1152 bytes) -- ignoring\n0.00.580.822 W model has unused tensor blk.45.ffn_gate_exps.weight (size = 1038090240 bytes) -- ignoring\n0.00.580.823 W model has unused tensor blk.45.ffn_up_exps.weight (size = 1038090240 bytes) -- ignoring\n0.00.580.825 W model has unused tensor blk.45.ffn_down_exps.weight (size = 1358954496 bytes) -- ignoring\n0.00.580.826 W model has unused tensor blk.45.ffn_gate_shexp.weight (size = 8912896 bytes) -- ignoring\n0.00.580.828 W model has unused tensor blk.45.ffn_up_shexp.weight (size = 8912896 bytes) -- ignoring\n0.00.580.829 W model has unused tensor blk.45.ffn_down_shexp.weight (size = 8912896 bytes) -- ignoring\n0.00.580.831 W model has unused tensor blk.45.nextn.eh_proj.weight (size = 35651584 bytes) -- ignoring\n0.00.580.833 W model has unused tensor blk.45.nextn.enorm.weight (size = 16384 bytes) -- ignoring\n0.00.580.835 W model has unused tensor blk.45.nextn.hnorm.weight (size = 16384 bytes) -- ignoring\n0.00.580.836 W model has unused tensor blk.45.nextn.shared_head_norm.weight (size = 16384 bytes) -- ignoring"
}