# RCO per-tensor GGUF allocation # Repository: ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF # GGUF: Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp.gguf # Source: https://huggingface.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF/resolve/main/Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp.gguf # Target whole-file bpw: 3.50 # GGUF version: 3 # GGUF metadata entries: 53 # Tensor count: 866 # Quant-type counts: BF16=96, F32=360, IQ1_M=1, IQ2_S=17, IQ2_XS=9, IQ2_XXS=5, IQ3_S=144, IQ3_XXS=78, IQ4_XS=96, Q2_K=13, Q4_K=39, Q6_K=8 # Format: : # Includes fixed non-RCO tensors (e.g. F32/BF16) so the released GGUF is fully reproducible. # Includes the 15-tensor MTP head (blk.64) for speculative decoding; whole-file bpw with the head: 3.5457 # output.weight: Q4_K output_norm.weight: F32 token_embd.weight: IQ2_S blk.0.attn_gate.weight: IQ4_XS blk.0.attn_norm.weight: F32 blk.0.attn_qkv.weight: IQ4_XS blk.0.ffn_down.weight: IQ2_S blk.0.ffn_gate.weight: IQ2_XS blk.0.ffn_up.weight: IQ2_XXS blk.0.post_attention_norm.weight: F32 blk.0.ssm_a: F32 blk.0.ssm_alpha.weight: BF16 blk.0.ssm_beta.weight: BF16 blk.0.ssm_conv1d.weight: F32 blk.0.ssm_dt.bias: F32 blk.0.ssm_norm.weight: F32 blk.0.ssm_out.weight: IQ4_XS blk.1.attn_gate.weight: IQ3_XXS blk.1.attn_norm.weight: F32 blk.1.attn_qkv.weight: IQ3_S blk.1.ffn_down.weight: IQ3_S blk.1.ffn_gate.weight: IQ2_XS blk.1.ffn_up.weight: IQ2_XXS blk.1.post_attention_norm.weight: F32 blk.1.ssm_a: F32 blk.1.ssm_alpha.weight: BF16 blk.1.ssm_beta.weight: BF16 blk.1.ssm_conv1d.weight: F32 blk.1.ssm_dt.bias: F32 blk.1.ssm_norm.weight: F32 blk.1.ssm_out.weight: Q4_K blk.2.attn_gate.weight: IQ3_S blk.2.attn_norm.weight: F32 blk.2.attn_qkv.weight: IQ3_XXS blk.2.ffn_down.weight: IQ3_S blk.2.ffn_gate.weight: IQ3_XXS blk.2.ffn_up.weight: IQ3_S blk.2.post_attention_norm.weight: F32 blk.2.ssm_a: F32 blk.2.ssm_alpha.weight: BF16 blk.2.ssm_beta.weight: BF16 blk.2.ssm_conv1d.weight: F32 blk.2.ssm_dt.bias: F32 blk.2.ssm_norm.weight: F32 blk.2.ssm_out.weight: IQ4_XS blk.3.attn_k.weight: IQ3_S blk.3.attn_k_norm.weight: F32 blk.3.attn_norm.weight: F32 blk.3.attn_output.weight: IQ3_S blk.3.attn_q.weight: IQ2_XXS blk.3.attn_q_norm.weight: F32 blk.3.attn_v.weight: IQ3_S blk.3.ffn_down.weight: IQ3_S blk.3.ffn_gate.weight: IQ3_XXS blk.3.ffn_up.weight: IQ3_XXS blk.3.post_attention_norm.weight: F32 blk.4.attn_gate.weight: IQ3_XXS blk.4.attn_norm.weight: F32 blk.4.attn_qkv.weight: IQ3_S blk.4.ffn_down.weight: IQ3_XXS blk.4.ffn_gate.weight: IQ3_XXS blk.4.ffn_up.weight: IQ3_XXS blk.4.post_attention_norm.weight: F32 blk.4.ssm_a: F32 blk.4.ssm_alpha.weight: BF16 blk.4.ssm_beta.weight: BF16 blk.4.ssm_conv1d.weight: F32 blk.4.ssm_dt.bias: F32 blk.4.ssm_norm.weight: F32 blk.4.ssm_out.weight: IQ3_S blk.5.attn_gate.weight: IQ3_S blk.5.attn_norm.weight: F32 blk.5.attn_qkv.weight: IQ3_S blk.5.ffn_down.weight: IQ4_XS blk.5.ffn_gate.weight: IQ3_S blk.5.ffn_up.weight: IQ2_S blk.5.post_attention_norm.weight: F32 blk.5.ssm_a: F32 blk.5.ssm_alpha.weight: BF16 blk.5.ssm_beta.weight: BF16 blk.5.ssm_conv1d.weight: F32 blk.5.ssm_dt.bias: F32 blk.5.ssm_norm.weight: F32 blk.5.ssm_out.weight: IQ4_XS blk.6.attn_gate.weight: IQ3_S blk.6.attn_norm.weight: F32 blk.6.attn_qkv.weight: IQ3_S blk.6.ffn_down.weight: IQ3_S blk.6.ffn_gate.weight: IQ3_S blk.6.ffn_up.weight: IQ3_S blk.6.post_attention_norm.weight: F32 blk.6.ssm_a: F32 blk.6.ssm_alpha.weight: BF16 blk.6.ssm_beta.weight: BF16 blk.6.ssm_conv1d.weight: F32 blk.6.ssm_dt.bias: F32 blk.6.ssm_norm.weight: F32 blk.6.ssm_out.weight: IQ3_S blk.7.attn_k.weight: IQ4_XS blk.7.attn_k_norm.weight: F32 blk.7.attn_norm.weight: F32 blk.7.attn_output.weight: IQ3_XXS blk.7.attn_q.weight: Q2_K blk.7.attn_q_norm.weight: F32 blk.7.attn_v.weight: IQ3_S blk.7.ffn_down.weight: IQ2_S blk.7.ffn_gate.weight: IQ2_S blk.7.ffn_up.weight: IQ3_XXS blk.7.post_attention_norm.weight: F32 blk.8.attn_gate.weight: IQ3_S blk.8.attn_norm.weight: F32 blk.8.attn_qkv.weight: IQ3_S blk.8.ffn_down.weight: IQ3_XXS blk.8.ffn_gate.weight: IQ3_XXS blk.8.ffn_up.weight: IQ3_XXS blk.8.post_attention_norm.weight: F32 blk.8.ssm_a: F32 blk.8.ssm_alpha.weight: BF16 blk.8.ssm_beta.weight: BF16 blk.8.ssm_conv1d.weight: F32 blk.8.ssm_dt.bias: F32 blk.8.ssm_norm.weight: F32 blk.8.ssm_out.weight: IQ3_XXS blk.9.attn_gate.weight: Q2_K blk.9.attn_norm.weight: F32 blk.9.attn_qkv.weight: IQ3_S blk.9.ffn_down.weight: IQ3_S blk.9.ffn_gate.weight: IQ2_S blk.9.ffn_up.weight: IQ3_S blk.9.post_attention_norm.weight: F32 blk.9.ssm_a: F32 blk.9.ssm_alpha.weight: BF16 blk.9.ssm_beta.weight: BF16 blk.9.ssm_conv1d.weight: F32 blk.9.ssm_dt.bias: F32 blk.9.ssm_norm.weight: F32 blk.9.ssm_out.weight: IQ3_XXS blk.10.attn_gate.weight: Q2_K blk.10.attn_norm.weight: F32 blk.10.attn_qkv.weight: IQ3_XXS blk.10.ffn_down.weight: IQ2_S blk.10.ffn_gate.weight: IQ3_XXS blk.10.ffn_up.weight: IQ3_XXS blk.10.post_attention_norm.weight: F32 blk.10.ssm_a: F32 blk.10.ssm_alpha.weight: BF16 blk.10.ssm_beta.weight: BF16 blk.10.ssm_conv1d.weight: F32 blk.10.ssm_dt.bias: F32 blk.10.ssm_norm.weight: F32 blk.10.ssm_out.weight: IQ3_S blk.11.attn_k.weight: IQ2_S blk.11.attn_k_norm.weight: F32 blk.11.attn_norm.weight: F32 blk.11.attn_output.weight: IQ3_S blk.11.attn_q.weight: Q2_K blk.11.attn_q_norm.weight: F32 blk.11.attn_v.weight: IQ3_XXS blk.11.ffn_down.weight: IQ2_XS blk.11.ffn_gate.weight: IQ2_XS blk.11.ffn_up.weight: IQ3_XXS blk.11.post_attention_norm.weight: F32 blk.12.attn_gate.weight: Q2_K blk.12.attn_norm.weight: F32 blk.12.attn_qkv.weight: IQ3_XXS blk.12.ffn_down.weight: IQ3_XXS blk.12.ffn_gate.weight: IQ2_S blk.12.ffn_up.weight: IQ2_XS blk.12.post_attention_norm.weight: F32 blk.12.ssm_a: F32 blk.12.ssm_alpha.weight: BF16 blk.12.ssm_beta.weight: BF16 blk.12.ssm_conv1d.weight: F32 blk.12.ssm_dt.bias: F32 blk.12.ssm_norm.weight: F32 blk.12.ssm_out.weight: IQ3_S blk.13.attn_gate.weight: Q2_K blk.13.attn_norm.weight: F32 blk.13.attn_qkv.weight: IQ3_XXS blk.13.ffn_down.weight: IQ3_XXS blk.13.ffn_gate.weight: IQ1_M blk.13.ffn_up.weight: IQ2_S blk.13.post_attention_norm.weight: F32 blk.13.ssm_a: F32 blk.13.ssm_alpha.weight: BF16 blk.13.ssm_beta.weight: BF16 blk.13.ssm_conv1d.weight: F32 blk.13.ssm_dt.bias: F32 blk.13.ssm_norm.weight: F32 blk.13.ssm_out.weight: IQ3_S blk.14.attn_gate.weight: IQ3_XXS blk.14.attn_norm.weight: F32 blk.14.attn_qkv.weight: IQ2_XS blk.14.ffn_down.weight: IQ2_S blk.14.ffn_gate.weight: IQ2_XXS blk.14.ffn_up.weight: IQ2_S blk.14.post_attention_norm.weight: F32 blk.14.ssm_a: F32 blk.14.ssm_alpha.weight: BF16 blk.14.ssm_beta.weight: BF16 blk.14.ssm_conv1d.weight: F32 blk.14.ssm_dt.bias: F32 blk.14.ssm_norm.weight: F32 blk.14.ssm_out.weight: IQ3_S blk.15.attn_k.weight: Q4_K blk.15.attn_k_norm.weight: F32 blk.15.attn_norm.weight: F32 blk.15.attn_output.weight: IQ3_S blk.15.attn_q.weight: Q2_K blk.15.attn_q_norm.weight: F32 blk.15.attn_v.weight: IQ3_S blk.15.ffn_down.weight: IQ2_XS blk.15.ffn_gate.weight: IQ3_XXS blk.15.ffn_up.weight: IQ3_XXS blk.15.post_attention_norm.weight: F32 blk.16.attn_gate.weight: IQ4_XS blk.16.attn_norm.weight: F32 blk.16.attn_qkv.weight: IQ3_XXS blk.16.ffn_down.weight: Q2_K blk.16.ffn_gate.weight: IQ2_XS blk.16.ffn_up.weight: IQ3_XXS blk.16.post_attention_norm.weight: F32 blk.16.ssm_a: F32 blk.16.ssm_alpha.weight: BF16 blk.16.ssm_beta.weight: BF16 blk.16.ssm_conv1d.weight: F32 blk.16.ssm_dt.bias: F32 blk.16.ssm_norm.weight: F32 blk.16.ssm_out.weight: IQ3_S blk.17.attn_gate.weight: IQ2_S blk.17.attn_norm.weight: F32 blk.17.attn_qkv.weight: IQ3_S blk.17.ffn_down.weight: IQ2_XS blk.17.ffn_gate.weight: IQ2_S blk.17.ffn_up.weight: IQ3_S blk.17.post_attention_norm.weight: F32 blk.17.ssm_a: F32 blk.17.ssm_alpha.weight: BF16 blk.17.ssm_beta.weight: BF16 blk.17.ssm_conv1d.weight: F32 blk.17.ssm_dt.bias: F32 blk.17.ssm_norm.weight: F32 blk.17.ssm_out.weight: IQ3_XXS blk.18.attn_gate.weight: IQ3_XXS blk.18.attn_norm.weight: F32 blk.18.attn_qkv.weight: Q2_K blk.18.ffn_down.weight: IQ3_S blk.18.ffn_gate.weight: IQ3_XXS blk.18.ffn_up.weight: IQ2_S blk.18.post_attention_norm.weight: F32 blk.18.ssm_a: F32 blk.18.ssm_alpha.weight: BF16 blk.18.ssm_beta.weight: BF16 blk.18.ssm_conv1d.weight: F32 blk.18.ssm_dt.bias: F32 blk.18.ssm_norm.weight: F32 blk.18.ssm_out.weight: IQ3_S blk.19.attn_k.weight: IQ3_XXS blk.19.attn_k_norm.weight: F32 blk.19.attn_norm.weight: F32 blk.19.attn_output.weight: IQ3_S blk.19.attn_q.weight: Q2_K blk.19.attn_q_norm.weight: F32 blk.19.attn_v.weight: IQ3_S blk.19.ffn_down.weight: IQ3_S blk.19.ffn_gate.weight: IQ3_XXS blk.19.ffn_up.weight: IQ3_XXS blk.19.post_attention_norm.weight: F32 blk.20.attn_gate.weight: Q4_K blk.20.attn_norm.weight: F32 blk.20.attn_qkv.weight: IQ3_XXS blk.20.ffn_down.weight: IQ3_XXS blk.20.ffn_gate.weight: IQ3_XXS blk.20.ffn_up.weight: IQ3_XXS blk.20.post_attention_norm.weight: F32 blk.20.ssm_a: F32 blk.20.ssm_alpha.weight: BF16 blk.20.ssm_beta.weight: BF16 blk.20.ssm_conv1d.weight: F32 blk.20.ssm_dt.bias: F32 blk.20.ssm_norm.weight: F32 blk.20.ssm_out.weight: IQ3_S blk.21.attn_gate.weight: IQ4_XS blk.21.attn_norm.weight: F32 blk.21.attn_qkv.weight: IQ3_S blk.21.ffn_down.weight: IQ4_XS blk.21.ffn_gate.weight: IQ3_XXS blk.21.ffn_up.weight: IQ3_XXS blk.21.post_attention_norm.weight: F32 blk.21.ssm_a: F32 blk.21.ssm_alpha.weight: BF16 blk.21.ssm_beta.weight: BF16 blk.21.ssm_conv1d.weight: F32 blk.21.ssm_dt.bias: F32 blk.21.ssm_norm.weight: F32 blk.21.ssm_out.weight: IQ3_S blk.22.attn_gate.weight: IQ3_S blk.22.attn_norm.weight: F32 blk.22.attn_qkv.weight: IQ3_XXS blk.22.ffn_down.weight: IQ3_S blk.22.ffn_gate.weight: IQ3_XXS blk.22.ffn_up.weight: IQ3_S blk.22.post_attention_norm.weight: F32 blk.22.ssm_a: F32 blk.22.ssm_alpha.weight: BF16 blk.22.ssm_beta.weight: BF16 blk.22.ssm_conv1d.weight: F32 blk.22.ssm_dt.bias: F32 blk.22.ssm_norm.weight: F32 blk.22.ssm_out.weight: IQ3_S blk.23.attn_k.weight: Q4_K blk.23.attn_k_norm.weight: F32 blk.23.attn_norm.weight: F32 blk.23.attn_output.weight: IQ3_S blk.23.attn_q.weight: IQ3_S blk.23.attn_q_norm.weight: F32 blk.23.attn_v.weight: Q4_K blk.23.ffn_down.weight: IQ3_S blk.23.ffn_gate.weight: IQ3_S blk.23.ffn_up.weight: IQ3_S blk.23.post_attention_norm.weight: F32 blk.24.attn_gate.weight: IQ3_S blk.24.attn_norm.weight: F32 blk.24.attn_qkv.weight: IQ3_S blk.24.ffn_down.weight: IQ4_XS blk.24.ffn_gate.weight: IQ3_S blk.24.ffn_up.weight: IQ3_S blk.24.post_attention_norm.weight: F32 blk.24.ssm_a: F32 blk.24.ssm_alpha.weight: BF16 blk.24.ssm_beta.weight: BF16 blk.24.ssm_conv1d.weight: F32 blk.24.ssm_dt.bias: F32 blk.24.ssm_norm.weight: F32 blk.24.ssm_out.weight: IQ3_S blk.25.attn_gate.weight: IQ3_S blk.25.attn_norm.weight: F32 blk.25.attn_qkv.weight: IQ3_XXS blk.25.ffn_down.weight: IQ3_S blk.25.ffn_gate.weight: IQ3_S blk.25.ffn_up.weight: IQ3_S blk.25.post_attention_norm.weight: F32 blk.25.ssm_a: F32 blk.25.ssm_alpha.weight: BF16 blk.25.ssm_beta.weight: BF16 blk.25.ssm_conv1d.weight: F32 blk.25.ssm_dt.bias: F32 blk.25.ssm_norm.weight: F32 blk.25.ssm_out.weight: IQ3_S blk.26.attn_gate.weight: IQ4_XS blk.26.attn_norm.weight: F32 blk.26.attn_qkv.weight: IQ3_S blk.26.ffn_down.weight: IQ3_S blk.26.ffn_gate.weight: IQ3_XXS blk.26.ffn_up.weight: IQ4_XS blk.26.post_attention_norm.weight: F32 blk.26.ssm_a: F32 blk.26.ssm_alpha.weight: BF16 blk.26.ssm_beta.weight: BF16 blk.26.ssm_conv1d.weight: F32 blk.26.ssm_dt.bias: F32 blk.26.ssm_norm.weight: F32 blk.26.ssm_out.weight: IQ3_S blk.27.attn_k.weight: IQ4_XS blk.27.attn_k_norm.weight: F32 blk.27.attn_norm.weight: F32 blk.27.attn_output.weight: IQ3_S blk.27.attn_q.weight: IQ4_XS blk.27.attn_q_norm.weight: F32 blk.27.attn_v.weight: Q4_K blk.27.ffn_down.weight: IQ3_S blk.27.ffn_gate.weight: IQ3_XXS blk.27.ffn_up.weight: IQ4_XS blk.27.post_attention_norm.weight: F32 blk.28.attn_gate.weight: IQ3_S blk.28.attn_norm.weight: F32 blk.28.attn_qkv.weight: IQ3_S blk.28.ffn_down.weight: Q4_K blk.28.ffn_gate.weight: Q2_K blk.28.ffn_up.weight: IQ3_S blk.28.post_attention_norm.weight: F32 blk.28.ssm_a: F32 blk.28.ssm_alpha.weight: BF16 blk.28.ssm_beta.weight: BF16 blk.28.ssm_conv1d.weight: F32 blk.28.ssm_dt.bias: F32 blk.28.ssm_norm.weight: F32 blk.28.ssm_out.weight: IQ4_XS blk.29.attn_gate.weight: IQ3_XXS blk.29.attn_norm.weight: F32 blk.29.attn_qkv.weight: IQ3_XXS blk.29.ffn_down.weight: IQ3_XXS blk.29.ffn_gate.weight: IQ3_XXS blk.29.ffn_up.weight: IQ3_XXS blk.29.post_attention_norm.weight: F32 blk.29.ssm_a: F32 blk.29.ssm_alpha.weight: BF16 blk.29.ssm_beta.weight: BF16 blk.29.ssm_conv1d.weight: F32 blk.29.ssm_dt.bias: F32 blk.29.ssm_norm.weight: F32 blk.29.ssm_out.weight: IQ4_XS blk.30.attn_gate.weight: IQ3_S blk.30.attn_norm.weight: F32 blk.30.attn_qkv.weight: IQ3_S blk.30.ffn_down.weight: IQ3_S blk.30.ffn_gate.weight: IQ3_XXS blk.30.ffn_up.weight: IQ3_XXS blk.30.post_attention_norm.weight: F32 blk.30.ssm_a: F32 blk.30.ssm_alpha.weight: BF16 blk.30.ssm_beta.weight: BF16 blk.30.ssm_conv1d.weight: F32 blk.30.ssm_dt.bias: F32 blk.30.ssm_norm.weight: F32 blk.30.ssm_out.weight: IQ4_XS blk.31.attn_k.weight: IQ4_XS blk.31.attn_k_norm.weight: F32 blk.31.attn_norm.weight: F32 blk.31.attn_output.weight: IQ3_S blk.31.attn_q.weight: Q2_K blk.31.attn_q_norm.weight: F32 blk.31.attn_v.weight: Q4_K blk.31.ffn_down.weight: IQ3_S blk.31.ffn_gate.weight: IQ3_XXS blk.31.ffn_up.weight: IQ3_XXS blk.31.post_attention_norm.weight: F32 blk.32.attn_gate.weight: IQ3_S blk.32.attn_norm.weight: F32 blk.32.attn_qkv.weight: IQ4_XS blk.32.ffn_down.weight: IQ3_S blk.32.ffn_gate.weight: IQ3_XXS blk.32.ffn_up.weight: IQ3_XXS blk.32.post_attention_norm.weight: F32 blk.32.ssm_a: F32 blk.32.ssm_alpha.weight: BF16 blk.32.ssm_beta.weight: BF16 blk.32.ssm_conv1d.weight: F32 blk.32.ssm_dt.bias: F32 blk.32.ssm_norm.weight: F32 blk.32.ssm_out.weight: IQ4_XS blk.33.attn_gate.weight: IQ3_S blk.33.attn_norm.weight: F32 blk.33.attn_qkv.weight: IQ3_S blk.33.ffn_down.weight: IQ3_XXS blk.33.ffn_gate.weight: IQ3_XXS blk.33.ffn_up.weight: IQ2_S blk.33.post_attention_norm.weight: F32 blk.33.ssm_a: F32 blk.33.ssm_alpha.weight: BF16 blk.33.ssm_beta.weight: BF16 blk.33.ssm_conv1d.weight: F32 blk.33.ssm_dt.bias: F32 blk.33.ssm_norm.weight: F32 blk.33.ssm_out.weight: IQ3_XXS blk.34.attn_gate.weight: IQ3_XXS blk.34.attn_norm.weight: F32 blk.34.attn_qkv.weight: IQ3_S blk.34.ffn_down.weight: IQ3_S blk.34.ffn_gate.weight: IQ3_XXS blk.34.ffn_up.weight: IQ4_XS blk.34.post_attention_norm.weight: F32 blk.34.ssm_a: F32 blk.34.ssm_alpha.weight: BF16 blk.34.ssm_beta.weight: BF16 blk.34.ssm_conv1d.weight: F32 blk.34.ssm_dt.bias: F32 blk.34.ssm_norm.weight: F32 blk.34.ssm_out.weight: IQ3_S blk.35.attn_k.weight: IQ4_XS blk.35.attn_k_norm.weight: F32 blk.35.attn_norm.weight: F32 blk.35.attn_output.weight: IQ4_XS blk.35.attn_q.weight: IQ3_S blk.35.attn_q_norm.weight: F32 blk.35.attn_v.weight: Q4_K blk.35.ffn_down.weight: IQ4_XS blk.35.ffn_gate.weight: IQ3_XXS blk.35.ffn_up.weight: IQ3_S blk.35.post_attention_norm.weight: F32 blk.36.attn_gate.weight: IQ3_S blk.36.attn_norm.weight: F32 blk.36.attn_qkv.weight: IQ4_XS blk.36.ffn_down.weight: IQ4_XS blk.36.ffn_gate.weight: IQ3_S blk.36.ffn_up.weight: Q4_K blk.36.post_attention_norm.weight: F32 blk.36.ssm_a: F32 blk.36.ssm_alpha.weight: BF16 blk.36.ssm_beta.weight: BF16 blk.36.ssm_conv1d.weight: F32 blk.36.ssm_dt.bias: F32 blk.36.ssm_norm.weight: F32 blk.36.ssm_out.weight: IQ4_XS blk.37.attn_gate.weight: Q4_K blk.37.attn_norm.weight: F32 blk.37.attn_qkv.weight: IQ3_S blk.37.ffn_down.weight: IQ4_XS blk.37.ffn_gate.weight: Q4_K blk.37.ffn_up.weight: IQ4_XS blk.37.post_attention_norm.weight: F32 blk.37.ssm_a: F32 blk.37.ssm_alpha.weight: BF16 blk.37.ssm_beta.weight: BF16 blk.37.ssm_conv1d.weight: F32 blk.37.ssm_dt.bias: F32 blk.37.ssm_norm.weight: F32 blk.37.ssm_out.weight: IQ4_XS blk.38.attn_gate.weight: IQ3_S blk.38.attn_norm.weight: F32 blk.38.attn_qkv.weight: IQ4_XS blk.38.ffn_down.weight: IQ4_XS blk.38.ffn_gate.weight: IQ3_S blk.38.ffn_up.weight: IQ3_XXS blk.38.post_attention_norm.weight: F32 blk.38.ssm_a: F32 blk.38.ssm_alpha.weight: BF16 blk.38.ssm_beta.weight: BF16 blk.38.ssm_conv1d.weight: F32 blk.38.ssm_dt.bias: F32 blk.38.ssm_norm.weight: F32 blk.38.ssm_out.weight: IQ3_S blk.39.attn_k.weight: IQ4_XS blk.39.attn_k_norm.weight: F32 blk.39.attn_norm.weight: F32 blk.39.attn_output.weight: Q4_K blk.39.attn_q.weight: IQ3_S blk.39.attn_q_norm.weight: F32 blk.39.attn_v.weight: IQ4_XS blk.39.ffn_down.weight: IQ4_XS blk.39.ffn_gate.weight: IQ4_XS blk.39.ffn_up.weight: IQ3_S blk.39.post_attention_norm.weight: F32 blk.40.attn_gate.weight: IQ3_XXS blk.40.attn_norm.weight: F32 blk.40.attn_qkv.weight: IQ3_S blk.40.ffn_down.weight: IQ4_XS blk.40.ffn_gate.weight: IQ4_XS blk.40.ffn_up.weight: IQ4_XS blk.40.post_attention_norm.weight: F32 blk.40.ssm_a: F32 blk.40.ssm_alpha.weight: BF16 blk.40.ssm_beta.weight: BF16 blk.40.ssm_conv1d.weight: F32 blk.40.ssm_dt.bias: F32 blk.40.ssm_norm.weight: F32 blk.40.ssm_out.weight: IQ4_XS blk.41.attn_gate.weight: IQ3_S blk.41.attn_norm.weight: F32 blk.41.attn_qkv.weight: IQ3_XXS blk.41.ffn_down.weight: IQ3_S blk.41.ffn_gate.weight: IQ3_S blk.41.ffn_up.weight: IQ3_XXS blk.41.post_attention_norm.weight: F32 blk.41.ssm_a: F32 blk.41.ssm_alpha.weight: BF16 blk.41.ssm_beta.weight: BF16 blk.41.ssm_conv1d.weight: F32 blk.41.ssm_dt.bias: F32 blk.41.ssm_norm.weight: F32 blk.41.ssm_out.weight: IQ3_S blk.42.attn_gate.weight: IQ3_XXS blk.42.attn_norm.weight: F32 blk.42.attn_qkv.weight: IQ4_XS blk.42.ffn_down.weight: Q4_K blk.42.ffn_gate.weight: IQ3_S blk.42.ffn_up.weight: IQ4_XS blk.42.post_attention_norm.weight: F32 blk.42.ssm_a: F32 blk.42.ssm_alpha.weight: BF16 blk.42.ssm_beta.weight: BF16 blk.42.ssm_conv1d.weight: F32 blk.42.ssm_dt.bias: F32 blk.42.ssm_norm.weight: F32 blk.42.ssm_out.weight: IQ3_S blk.43.attn_k.weight: Q4_K blk.43.attn_k_norm.weight: F32 blk.43.attn_norm.weight: F32 blk.43.attn_output.weight: IQ4_XS blk.43.attn_q.weight: IQ4_XS blk.43.attn_q_norm.weight: F32 blk.43.attn_v.weight: Q4_K blk.43.ffn_down.weight: IQ3_S blk.43.ffn_gate.weight: IQ4_XS blk.43.ffn_up.weight: IQ4_XS blk.43.post_attention_norm.weight: F32 blk.44.attn_gate.weight: IQ4_XS blk.44.attn_norm.weight: F32 blk.44.attn_qkv.weight: IQ4_XS blk.44.ffn_down.weight: IQ4_XS blk.44.ffn_gate.weight: IQ3_S blk.44.ffn_up.weight: IQ4_XS blk.44.post_attention_norm.weight: F32 blk.44.ssm_a: F32 blk.44.ssm_alpha.weight: BF16 blk.44.ssm_beta.weight: BF16 blk.44.ssm_conv1d.weight: F32 blk.44.ssm_dt.bias: F32 blk.44.ssm_norm.weight: F32 blk.44.ssm_out.weight: IQ4_XS blk.45.attn_gate.weight: IQ3_XXS blk.45.attn_norm.weight: F32 blk.45.attn_qkv.weight: IQ3_S blk.45.ffn_down.weight: IQ3_S blk.45.ffn_gate.weight: IQ3_S blk.45.ffn_up.weight: IQ3_XXS blk.45.post_attention_norm.weight: F32 blk.45.ssm_a: F32 blk.45.ssm_alpha.weight: BF16 blk.45.ssm_beta.weight: BF16 blk.45.ssm_conv1d.weight: F32 blk.45.ssm_dt.bias: F32 blk.45.ssm_norm.weight: F32 blk.45.ssm_out.weight: IQ3_S blk.46.attn_gate.weight: IQ3_S blk.46.attn_norm.weight: F32 blk.46.attn_qkv.weight: IQ3_XXS blk.46.ffn_down.weight: IQ3_S blk.46.ffn_gate.weight: IQ3_S blk.46.ffn_up.weight: IQ3_S blk.46.post_attention_norm.weight: F32 blk.46.ssm_a: F32 blk.46.ssm_alpha.weight: BF16 blk.46.ssm_beta.weight: BF16 blk.46.ssm_conv1d.weight: F32 blk.46.ssm_dt.bias: F32 blk.46.ssm_norm.weight: F32 blk.46.ssm_out.weight: Q4_K blk.47.attn_k.weight: IQ4_XS blk.47.attn_k_norm.weight: F32 blk.47.attn_norm.weight: F32 blk.47.attn_output.weight: IQ3_S blk.47.attn_q.weight: IQ3_XXS blk.47.attn_q_norm.weight: F32 blk.47.attn_v.weight: Q4_K blk.47.ffn_down.weight: IQ4_XS blk.47.ffn_gate.weight: Q4_K blk.47.ffn_up.weight: IQ3_S blk.47.post_attention_norm.weight: F32 blk.48.attn_gate.weight: IQ2_S blk.48.attn_norm.weight: F32 blk.48.attn_qkv.weight: IQ3_XXS blk.48.ffn_down.weight: IQ3_S blk.48.ffn_gate.weight: IQ4_XS blk.48.ffn_up.weight: IQ3_S blk.48.post_attention_norm.weight: F32 blk.48.ssm_a: F32 blk.48.ssm_alpha.weight: BF16 blk.48.ssm_beta.weight: BF16 blk.48.ssm_conv1d.weight: F32 blk.48.ssm_dt.bias: F32 blk.48.ssm_norm.weight: F32 blk.48.ssm_out.weight: Q4_K blk.49.attn_gate.weight: IQ3_S blk.49.attn_norm.weight: F32 blk.49.attn_qkv.weight: Q4_K blk.49.ffn_down.weight: IQ4_XS blk.49.ffn_gate.weight: IQ3_XXS blk.49.ffn_up.weight: IQ3_S blk.49.post_attention_norm.weight: F32 blk.49.ssm_a: F32 blk.49.ssm_alpha.weight: BF16 blk.49.ssm_beta.weight: BF16 blk.49.ssm_conv1d.weight: F32 blk.49.ssm_dt.bias: F32 blk.49.ssm_norm.weight: F32 blk.49.ssm_out.weight: Q4_K blk.50.attn_gate.weight: IQ4_XS blk.50.attn_norm.weight: F32 blk.50.attn_qkv.weight: IQ4_XS blk.50.ffn_down.weight: IQ4_XS blk.50.ffn_gate.weight: IQ4_XS blk.50.ffn_up.weight: IQ3_S blk.50.post_attention_norm.weight: F32 blk.50.ssm_a: F32 blk.50.ssm_alpha.weight: BF16 blk.50.ssm_beta.weight: BF16 blk.50.ssm_conv1d.weight: F32 blk.50.ssm_dt.bias: F32 blk.50.ssm_norm.weight: F32 blk.50.ssm_out.weight: IQ4_XS blk.51.attn_k.weight: Q4_K blk.51.attn_k_norm.weight: F32 blk.51.attn_norm.weight: F32 blk.51.attn_output.weight: Q4_K blk.51.attn_q.weight: IQ3_XXS blk.51.attn_q_norm.weight: F32 blk.51.attn_v.weight: Q4_K blk.51.ffn_down.weight: Q4_K blk.51.ffn_gate.weight: IQ3_S blk.51.ffn_up.weight: IQ3_S blk.51.post_attention_norm.weight: F32 blk.52.attn_gate.weight: IQ4_XS blk.52.attn_norm.weight: F32 blk.52.attn_qkv.weight: IQ3_S blk.52.ffn_down.weight: Q4_K blk.52.ffn_gate.weight: IQ4_XS blk.52.ffn_up.weight: IQ3_S blk.52.post_attention_norm.weight: F32 blk.52.ssm_a: F32 blk.52.ssm_alpha.weight: BF16 blk.52.ssm_beta.weight: BF16 blk.52.ssm_conv1d.weight: F32 blk.52.ssm_dt.bias: F32 blk.52.ssm_norm.weight: F32 blk.52.ssm_out.weight: IQ4_XS blk.53.attn_gate.weight: Q4_K blk.53.attn_norm.weight: F32 blk.53.attn_qkv.weight: IQ3_S blk.53.ffn_down.weight: Q4_K blk.53.ffn_gate.weight: IQ4_XS blk.53.ffn_up.weight: IQ3_S blk.53.post_attention_norm.weight: F32 blk.53.ssm_a: F32 blk.53.ssm_alpha.weight: BF16 blk.53.ssm_beta.weight: BF16 blk.53.ssm_conv1d.weight: F32 blk.53.ssm_dt.bias: F32 blk.53.ssm_norm.weight: F32 blk.53.ssm_out.weight: IQ4_XS blk.54.attn_gate.weight: IQ4_XS blk.54.attn_norm.weight: F32 blk.54.attn_qkv.weight: IQ4_XS blk.54.ffn_down.weight: IQ4_XS blk.54.ffn_gate.weight: IQ4_XS blk.54.ffn_up.weight: IQ3_S blk.54.post_attention_norm.weight: F32 blk.54.ssm_a: F32 blk.54.ssm_alpha.weight: BF16 blk.54.ssm_beta.weight: BF16 blk.54.ssm_conv1d.weight: F32 blk.54.ssm_dt.bias: F32 blk.54.ssm_norm.weight: F32 blk.54.ssm_out.weight: IQ4_XS blk.55.attn_k.weight: Q4_K blk.55.attn_k_norm.weight: F32 blk.55.attn_norm.weight: F32 blk.55.attn_output.weight: Q4_K blk.55.attn_q.weight: IQ3_XXS blk.55.attn_q_norm.weight: F32 blk.55.attn_v.weight: Q4_K blk.55.ffn_down.weight: IQ4_XS blk.55.ffn_gate.weight: IQ3_S blk.55.ffn_up.weight: IQ3_S blk.55.post_attention_norm.weight: F32 blk.56.attn_gate.weight: IQ4_XS blk.56.attn_norm.weight: F32 blk.56.attn_qkv.weight: IQ3_S blk.56.ffn_down.weight: Q4_K blk.56.ffn_gate.weight: IQ3_S blk.56.ffn_up.weight: IQ3_S blk.56.post_attention_norm.weight: F32 blk.56.ssm_a: F32 blk.56.ssm_alpha.weight: BF16 blk.56.ssm_beta.weight: BF16 blk.56.ssm_conv1d.weight: F32 blk.56.ssm_dt.bias: F32 blk.56.ssm_norm.weight: F32 blk.56.ssm_out.weight: Q4_K blk.57.attn_gate.weight: IQ3_S blk.57.attn_norm.weight: F32 blk.57.attn_qkv.weight: IQ3_S blk.57.ffn_down.weight: IQ4_XS blk.57.ffn_gate.weight: IQ4_XS blk.57.ffn_up.weight: IQ4_XS blk.57.post_attention_norm.weight: F32 blk.57.ssm_a: F32 blk.57.ssm_alpha.weight: BF16 blk.57.ssm_beta.weight: BF16 blk.57.ssm_conv1d.weight: F32 blk.57.ssm_dt.bias: F32 blk.57.ssm_norm.weight: F32 blk.57.ssm_out.weight: IQ4_XS blk.58.attn_gate.weight: IQ4_XS blk.58.attn_norm.weight: F32 blk.58.attn_qkv.weight: IQ2_XXS blk.58.ffn_down.weight: IQ4_XS blk.58.ffn_gate.weight: IQ4_XS blk.58.ffn_up.weight: Q4_K blk.58.post_attention_norm.weight: F32 blk.58.ssm_a: F32 blk.58.ssm_alpha.weight: BF16 blk.58.ssm_beta.weight: BF16 blk.58.ssm_conv1d.weight: F32 blk.58.ssm_dt.bias: F32 blk.58.ssm_norm.weight: F32 blk.58.ssm_out.weight: Q4_K blk.59.attn_k.weight: IQ4_XS blk.59.attn_k_norm.weight: F32 blk.59.attn_norm.weight: F32 blk.59.attn_output.weight: IQ3_S blk.59.attn_q.weight: Q2_K blk.59.attn_q_norm.weight: F32 blk.59.attn_v.weight: IQ3_S blk.59.ffn_down.weight: IQ4_XS blk.59.ffn_gate.weight: IQ4_XS blk.59.ffn_up.weight: IQ3_S blk.59.post_attention_norm.weight: F32 blk.60.attn_gate.weight: IQ4_XS blk.60.attn_norm.weight: F32 blk.60.attn_qkv.weight: IQ3_S blk.60.ffn_down.weight: IQ4_XS blk.60.ffn_gate.weight: IQ4_XS blk.60.ffn_up.weight: IQ3_S blk.60.post_attention_norm.weight: F32 blk.60.ssm_a: F32 blk.60.ssm_alpha.weight: BF16 blk.60.ssm_beta.weight: BF16 blk.60.ssm_conv1d.weight: F32 blk.60.ssm_dt.bias: F32 blk.60.ssm_norm.weight: F32 blk.60.ssm_out.weight: IQ3_S blk.61.attn_gate.weight: IQ4_XS blk.61.attn_norm.weight: F32 blk.61.attn_qkv.weight: IQ3_XXS blk.61.ffn_down.weight: IQ4_XS blk.61.ffn_gate.weight: IQ4_XS blk.61.ffn_up.weight: IQ3_S blk.61.post_attention_norm.weight: F32 blk.61.ssm_a: F32 blk.61.ssm_alpha.weight: BF16 blk.61.ssm_beta.weight: BF16 blk.61.ssm_conv1d.weight: F32 blk.61.ssm_dt.bias: F32 blk.61.ssm_norm.weight: F32 blk.61.ssm_out.weight: IQ3_S blk.62.attn_gate.weight: IQ3_S blk.62.attn_norm.weight: F32 blk.62.attn_qkv.weight: IQ4_XS blk.62.ffn_down.weight: IQ3_S blk.62.ffn_gate.weight: IQ4_XS blk.62.ffn_up.weight: Q4_K blk.62.post_attention_norm.weight: F32 blk.62.ssm_a: F32 blk.62.ssm_alpha.weight: BF16 blk.62.ssm_beta.weight: BF16 blk.62.ssm_conv1d.weight: F32 blk.62.ssm_dt.bias: F32 blk.62.ssm_norm.weight: F32 blk.62.ssm_out.weight: IQ3_S blk.63.attn_k.weight: IQ4_XS blk.63.attn_k_norm.weight: F32 blk.63.attn_norm.weight: F32 blk.63.attn_output.weight: IQ3_S blk.63.attn_q.weight: Q4_K blk.63.attn_q_norm.weight: F32 blk.63.attn_v.weight: IQ3_S blk.63.ffn_down.weight: IQ4_XS blk.63.ffn_gate.weight: IQ4_XS blk.63.ffn_up.weight: IQ4_XS blk.63.post_attention_norm.weight: F32 blk.64.attn_k.weight: Q6_K blk.64.attn_k_norm.weight: F32 blk.64.attn_norm.weight: F32 blk.64.attn_output.weight: Q6_K blk.64.attn_q.weight: Q6_K blk.64.attn_q_norm.weight: F32 blk.64.attn_v.weight: Q6_K blk.64.ffn_down.weight: Q6_K blk.64.ffn_gate.weight: Q6_K blk.64.ffn_up.weight: Q6_K blk.64.nextn.eh_proj.weight: Q6_K blk.64.nextn.enorm.weight: F32 blk.64.nextn.hnorm.weight: F32 blk.64.nextn.shared_head_norm.weight: F32 blk.64.post_attention_norm.weight: F32