# InternVL3-8B

Hugging Face: `OpenGVLab/InternVL3-8B`
Reconstructed from `config.json` alone. No weights were read.

| | |
|---|---|
| Derived from structure | 7,920,430,202 |
| In the published checkpoint | 7,944,373,760 (safetensors.total, 2025-09-11) |
| Delta | -0.30% |
| Comparability | custom-code |
| Layers | 273 |
| Priced on | A10G (24GB) |
| Est. one run | $13242.86 |

> This repository ships its own modeling code (`auto_map`, e.g. `configuration_internvl_chat.py`), so `config.json` names a class in the repo rather than an architecture `transformers` defines. The graph below is what those config keys mean under `transformers` semantics, which is not necessarily what the repo's own file builds. A gap here is a statement about what we read, not about the checkpoint.

## Structure

| # | Layer | Type | Output shape |
|---|---|---|---|
| 1 | Input | Input | 1 × 32768 |
| 2 | Embedding | Embedding | 1 × 32768 × 3584 |
| 3 | RoPE | RoPE | 1 × 32768 × 3584 |
| 4 | Vision input | Input | 3 × 448 × 448 |
| 5 | PatchEmbed | Patch Embed | 1024 × 1024 |
| 6 | Patch_Position_Embedding | Learned Pos Embed | 1024 × 1024 |
| 7 | Vision_LN_1 | LayerNorm | 1024 × 1024 |
| 8 | Vision_Attn_1 | Multi-Head Attention | 1024 × 1024 |
| 9 | Vision_Add_1 | Add | 1024 × 1024 |
| 10 | Vision_FFN_1 | Feed Forward | 1024 × 1024 |
| 11 | Vision_LN_2 | LayerNorm | 1024 × 1024 |
| 12 | Vision_Attn_2 | Multi-Head Attention | 1024 × 1024 |
| 13 | Vision_Add_2 | Add | 1024 × 1024 |
| 14 | Vision_FFN_2 | Feed Forward | 1024 × 1024 |
| 15 | Vision_LN_3 | LayerNorm | 1024 × 1024 |
| 16 | Vision_Attn_3 | Multi-Head Attention | 1024 × 1024 |
| 17 | Vision_Add_3 | Add | 1024 × 1024 |
| 18 | Vision_FFN_3 | Feed Forward | 1024 × 1024 |
| 19 | Vision_LN_4 | LayerNorm | 1024 × 1024 |
| 20 | Vision_Attn_4 | Multi-Head Attention | 1024 × 1024 |
| 21 | Vision_Add_4 | Add | 1024 × 1024 |
| 22 | Vision_FFN_4 | Feed Forward | 1024 × 1024 |
| 23 | Vision_LN_5 | LayerNorm | 1024 × 1024 |
| 24 | Vision_Attn_5 | Multi-Head Attention | 1024 × 1024 |
| 25 | Vision_Add_5 | Add | 1024 × 1024 |
| 26 | Vision_FFN_5 | Feed Forward | 1024 × 1024 |
| 27 | Vision_LN_6 | LayerNorm | 1024 × 1024 |
| 28 | Vision_Attn_6 | Multi-Head Attention | 1024 × 1024 |
| 29 | Vision_Add_6 | Add | 1024 × 1024 |
| 30 | Vision_FFN_6 | Feed Forward | 1024 × 1024 |
| 31 | Vision_LN_7 | LayerNorm | 1024 × 1024 |
| 32 | Vision_Attn_7 | Multi-Head Attention | 1024 × 1024 |
| 33 | Vision_Add_7 | Add | 1024 × 1024 |
| 34 | Vision_FFN_7 | Feed Forward | 1024 × 1024 |
| 35 | Vision_LN_8 | LayerNorm | 1024 × 1024 |
| 36 | Vision_Attn_8 | Multi-Head Attention | 1024 × 1024 |
| 37 | Vision_Add_8 | Add | 1024 × 1024 |
| 38 | Vision_FFN_8 | Feed Forward | 1024 × 1024 |
| 39 | Vision_LN_9 | LayerNorm | 1024 × 1024 |
| 40 | Vision_Attn_9 | Multi-Head Attention | 1024 × 1024 |
| 41 | Vision_Add_9 | Add | 1024 × 1024 |
| 42 | Vision_FFN_9 | Feed Forward | 1024 × 1024 |
| 43 | Vision_LN_10 | LayerNorm | 1024 × 1024 |
| 44 | Vision_Attn_10 | Multi-Head Attention | 1024 × 1024 |
| 45 | Vision_Add_10 | Add | 1024 × 1024 |
| 46 | Vision_FFN_10 | Feed Forward | 1024 × 1024 |
| 47 | Vision_LN_11 | LayerNorm | 1024 × 1024 |
| 48 | Vision_Attn_11 | Multi-Head Attention | 1024 × 1024 |
| 49 | Vision_Add_11 | Add | 1024 × 1024 |
| 50 | Vision_FFN_11 | Feed Forward | 1024 × 1024 |
| 51 | Vision_LN_12 | LayerNorm | 1024 × 1024 |
| 52 | Vision_Attn_12 | Multi-Head Attention | 1024 × 1024 |
| 53 | Vision_Add_12 | Add | 1024 × 1024 |
| 54 | Vision_FFN_12 | Feed Forward | 1024 × 1024 |
| 55 | Vision_LN_13 | LayerNorm | 1024 × 1024 |
| 56 | Vision_Attn_13 | Multi-Head Attention | 1024 × 1024 |
| 57 | Vision_Add_13 | Add | 1024 × 1024 |
| 58 | Vision_FFN_13 | Feed Forward | 1024 × 1024 |
| 59 | Vision_LN_14 | LayerNorm | 1024 × 1024 |
| 60 | Vision_Attn_14 | Multi-Head Attention | 1024 × 1024 |
| 61 | Vision_Add_14 | Add | 1024 × 1024 |
| 62 | Vision_FFN_14 | Feed Forward | 1024 × 1024 |
| 63 | Vision_LN_15 | LayerNorm | 1024 × 1024 |
| 64 | Vision_Attn_15 | Multi-Head Attention | 1024 × 1024 |
| 65 | Vision_Add_15 | Add | 1024 × 1024 |
| 66 | Vision_FFN_15 | Feed Forward | 1024 × 1024 |
| 67 | Vision_LN_16 | LayerNorm | 1024 × 1024 |
| 68 | Vision_Attn_16 | Multi-Head Attention | 1024 × 1024 |
| 69 | Vision_Add_16 | Add | 1024 × 1024 |
| 70 | Vision_FFN_16 | Feed Forward | 1024 × 1024 |
| 71 | Vision_LN_17 | LayerNorm | 1024 × 1024 |
| 72 | Vision_Attn_17 | Multi-Head Attention | 1024 × 1024 |
| 73 | Vision_Add_17 | Add | 1024 × 1024 |
| 74 | Vision_FFN_17 | Feed Forward | 1024 × 1024 |
| 75 | Vision_LN_18 | LayerNorm | 1024 × 1024 |
| 76 | Vision_Attn_18 | Multi-Head Attention | 1024 × 1024 |
| 77 | Vision_Add_18 | Add | 1024 × 1024 |
| 78 | Vision_FFN_18 | Feed Forward | 1024 × 1024 |
| 79 | Vision_LN_19 | LayerNorm | 1024 × 1024 |
| 80 | Vision_Attn_19 | Multi-Head Attention | 1024 × 1024 |
| 81 | Vision_Add_19 | Add | 1024 × 1024 |
| 82 | Vision_FFN_19 | Feed Forward | 1024 × 1024 |
| 83 | Vision_LN_20 | LayerNorm | 1024 × 1024 |
| 84 | Vision_Attn_20 | Multi-Head Attention | 1024 × 1024 |
| 85 | Vision_Add_20 | Add | 1024 × 1024 |
| 86 | Vision_FFN_20 | Feed Forward | 1024 × 1024 |
| 87 | Vision_LN_21 | LayerNorm | 1024 × 1024 |
| 88 | Vision_Attn_21 | Multi-Head Attention | 1024 × 1024 |
| 89 | Vision_Add_21 | Add | 1024 × 1024 |
| 90 | Vision_FFN_21 | Feed Forward | 1024 × 1024 |
| 91 | Vision_LN_22 | LayerNorm | 1024 × 1024 |
| 92 | Vision_Attn_22 | Multi-Head Attention | 1024 × 1024 |
| 93 | Vision_Add_22 | Add | 1024 × 1024 |
| 94 | Vision_FFN_22 | Feed Forward | 1024 × 1024 |
| 95 | Vision_LN_23 | LayerNorm | 1024 × 1024 |
| 96 | Vision_Attn_23 | Multi-Head Attention | 1024 × 1024 |
| 97 | Vision_Add_23 | Add | 1024 × 1024 |
| 98 | Vision_FFN_23 | Feed Forward | 1024 × 1024 |
| 99 | Vision_LN_24 | LayerNorm | 1024 × 1024 |
| 100 | Vision_Attn_24 | Multi-Head Attention | 1024 × 1024 |
| 101 | Vision_Add_24 | Add | 1024 × 1024 |
| 102 | Vision_FFN_24 | Feed Forward | 1024 × 1024 |
| 103 | Vision projector | Projection | 1024 × 3584 |
| 104 | Vision tokens | Reshape | 1 × 1024 × 3584 |
| 105 | Multimodal fusion (concat tokens) | Concatenate | 1 × 33792 × 3584 |
| 106 | RMSNorm_1_1 | RMSNorm | 1 × 33792 × 3584 |
| 107 | Attention_1 | Grouped Query Attn | 1 × 33792 × 3584 |
| 108 | Add_1_attn | Add | 1 × 33792 × 3584 |
| 109 | RMSNorm_1_2 | RMSNorm | 1 × 33792 × 3584 |
| 110 | FFN_1 | SwiGLU | 1 × 33792 × 3584 |
| 111 | Add_1_ffn | Add | 1 × 33792 × 3584 |
| 112 | RMSNorm_2_1 | RMSNorm | 1 × 33792 × 3584 |
| 113 | Attention_2 | Grouped Query Attn | 1 × 33792 × 3584 |
| 114 | Add_2_attn | Add | 1 × 33792 × 3584 |
| 115 | RMSNorm_2_2 | RMSNorm | 1 × 33792 × 3584 |
| 116 | FFN_2 | SwiGLU | 1 × 33792 × 3584 |
| 117 | Add_2_ffn | Add | 1 × 33792 × 3584 |
| 118 | RMSNorm_3_1 | RMSNorm | 1 × 33792 × 3584 |
| 119 | Attention_3 | Grouped Query Attn | 1 × 33792 × 3584 |
| 120 | Add_3_attn | Add | 1 × 33792 × 3584 |
| 121 | RMSNorm_3_2 | RMSNorm | 1 × 33792 × 3584 |
| 122 | FFN_3 | SwiGLU | 1 × 33792 × 3584 |
| 123 | Add_3_ffn | Add | 1 × 33792 × 3584 |
| 124 | RMSNorm_4_1 | RMSNorm | 1 × 33792 × 3584 |
| 125 | Attention_4 | Grouped Query Attn | 1 × 33792 × 3584 |
| 126 | Add_4_attn | Add | 1 × 33792 × 3584 |
| 127 | RMSNorm_4_2 | RMSNorm | 1 × 33792 × 3584 |
| 128 | FFN_4 | SwiGLU | 1 × 33792 × 3584 |
| 129 | Add_4_ffn | Add | 1 × 33792 × 3584 |
| 130 | RMSNorm_5_1 | RMSNorm | 1 × 33792 × 3584 |
| 131 | Attention_5 | Grouped Query Attn | 1 × 33792 × 3584 |
| 132 | Add_5_attn | Add | 1 × 33792 × 3584 |
| 133 | RMSNorm_5_2 | RMSNorm | 1 × 33792 × 3584 |
| 134 | FFN_5 | SwiGLU | 1 × 33792 × 3584 |
| 135 | Add_5_ffn | Add | 1 × 33792 × 3584 |
| 136 | RMSNorm_6_1 | RMSNorm | 1 × 33792 × 3584 |
| 137 | Attention_6 | Grouped Query Attn | 1 × 33792 × 3584 |
| 138 | Add_6_attn | Add | 1 × 33792 × 3584 |
| 139 | RMSNorm_6_2 | RMSNorm | 1 × 33792 × 3584 |
| 140 | FFN_6 | SwiGLU | 1 × 33792 × 3584 |
| 141 | Add_6_ffn | Add | 1 × 33792 × 3584 |
| 142 | RMSNorm_7_1 | RMSNorm | 1 × 33792 × 3584 |
| 143 | Attention_7 | Grouped Query Attn | 1 × 33792 × 3584 |
| 144 | Add_7_attn | Add | 1 × 33792 × 3584 |
| 145 | RMSNorm_7_2 | RMSNorm | 1 × 33792 × 3584 |
| 146 | FFN_7 | SwiGLU | 1 × 33792 × 3584 |
| 147 | Add_7_ffn | Add | 1 × 33792 × 3584 |
| 148 | RMSNorm_8_1 | RMSNorm | 1 × 33792 × 3584 |
| 149 | Attention_8 | Grouped Query Attn | 1 × 33792 × 3584 |
| 150 | Add_8_attn | Add | 1 × 33792 × 3584 |
| 151 | RMSNorm_8_2 | RMSNorm | 1 × 33792 × 3584 |
| 152 | FFN_8 | SwiGLU | 1 × 33792 × 3584 |
| 153 | Add_8_ffn | Add | 1 × 33792 × 3584 |
| 154 | RMSNorm_9_1 | RMSNorm | 1 × 33792 × 3584 |
| 155 | Attention_9 | Grouped Query Attn | 1 × 33792 × 3584 |
| 156 | Add_9_attn | Add | 1 × 33792 × 3584 |
| 157 | RMSNorm_9_2 | RMSNorm | 1 × 33792 × 3584 |
| 158 | FFN_9 | SwiGLU | 1 × 33792 × 3584 |
| 159 | Add_9_ffn | Add | 1 × 33792 × 3584 |
| 160 | RMSNorm_10_1 | RMSNorm | 1 × 33792 × 3584 |
| 161 | Attention_10 | Grouped Query Attn | 1 × 33792 × 3584 |
| 162 | Add_10_attn | Add | 1 × 33792 × 3584 |
| 163 | RMSNorm_10_2 | RMSNorm | 1 × 33792 × 3584 |
| 164 | FFN_10 | SwiGLU | 1 × 33792 × 3584 |
| 165 | Add_10_ffn | Add | 1 × 33792 × 3584 |
| 166 | RMSNorm_11_1 | RMSNorm | 1 × 33792 × 3584 |
| 167 | Attention_11 | Grouped Query Attn | 1 × 33792 × 3584 |
| 168 | Add_11_attn | Add | 1 × 33792 × 3584 |
| 169 | RMSNorm_11_2 | RMSNorm | 1 × 33792 × 3584 |
| 170 | FFN_11 | SwiGLU | 1 × 33792 × 3584 |
| 171 | Add_11_ffn | Add | 1 × 33792 × 3584 |
| 172 | RMSNorm_12_1 | RMSNorm | 1 × 33792 × 3584 |
| 173 | Attention_12 | Grouped Query Attn | 1 × 33792 × 3584 |
| 174 | Add_12_attn | Add | 1 × 33792 × 3584 |
| 175 | RMSNorm_12_2 | RMSNorm | 1 × 33792 × 3584 |
| 176 | FFN_12 | SwiGLU | 1 × 33792 × 3584 |
| 177 | Add_12_ffn | Add | 1 × 33792 × 3584 |
| 178 | RMSNorm_13_1 | RMSNorm | 1 × 33792 × 3584 |
| 179 | Attention_13 | Grouped Query Attn | 1 × 33792 × 3584 |
| 180 | Add_13_attn | Add | 1 × 33792 × 3584 |
| 181 | RMSNorm_13_2 | RMSNorm | 1 × 33792 × 3584 |
| 182 | FFN_13 | SwiGLU | 1 × 33792 × 3584 |
| 183 | Add_13_ffn | Add | 1 × 33792 × 3584 |
| 184 | RMSNorm_14_1 | RMSNorm | 1 × 33792 × 3584 |
| 185 | Attention_14 | Grouped Query Attn | 1 × 33792 × 3584 |
| 186 | Add_14_attn | Add | 1 × 33792 × 3584 |
| 187 | RMSNorm_14_2 | RMSNorm | 1 × 33792 × 3584 |
| 188 | FFN_14 | SwiGLU | 1 × 33792 × 3584 |
| 189 | Add_14_ffn | Add | 1 × 33792 × 3584 |
| 190 | RMSNorm_15_1 | RMSNorm | 1 × 33792 × 3584 |
| 191 | Attention_15 | Grouped Query Attn | 1 × 33792 × 3584 |
| 192 | Add_15_attn | Add | 1 × 33792 × 3584 |
| 193 | RMSNorm_15_2 | RMSNorm | 1 × 33792 × 3584 |
| 194 | FFN_15 | SwiGLU | 1 × 33792 × 3584 |
| 195 | Add_15_ffn | Add | 1 × 33792 × 3584 |
| 196 | RMSNorm_16_1 | RMSNorm | 1 × 33792 × 3584 |
| 197 | Attention_16 | Grouped Query Attn | 1 × 33792 × 3584 |
| 198 | Add_16_attn | Add | 1 × 33792 × 3584 |
| 199 | RMSNorm_16_2 | RMSNorm | 1 × 33792 × 3584 |
| 200 | FFN_16 | SwiGLU | 1 × 33792 × 3584 |
| 201 | Add_16_ffn | Add | 1 × 33792 × 3584 |
| 202 | RMSNorm_17_1 | RMSNorm | 1 × 33792 × 3584 |
| 203 | Attention_17 | Grouped Query Attn | 1 × 33792 × 3584 |
| 204 | Add_17_attn | Add | 1 × 33792 × 3584 |
| 205 | RMSNorm_17_2 | RMSNorm | 1 × 33792 × 3584 |
| 206 | FFN_17 | SwiGLU | 1 × 33792 × 3584 |
| 207 | Add_17_ffn | Add | 1 × 33792 × 3584 |
| 208 | RMSNorm_18_1 | RMSNorm | 1 × 33792 × 3584 |
| 209 | Attention_18 | Grouped Query Attn | 1 × 33792 × 3584 |
| 210 | Add_18_attn | Add | 1 × 33792 × 3584 |
| 211 | RMSNorm_18_2 | RMSNorm | 1 × 33792 × 3584 |
| 212 | FFN_18 | SwiGLU | 1 × 33792 × 3584 |
| 213 | Add_18_ffn | Add | 1 × 33792 × 3584 |
| 214 | RMSNorm_19_1 | RMSNorm | 1 × 33792 × 3584 |
| 215 | Attention_19 | Grouped Query Attn | 1 × 33792 × 3584 |
| 216 | Add_19_attn | Add | 1 × 33792 × 3584 |
| 217 | RMSNorm_19_2 | RMSNorm | 1 × 33792 × 3584 |
| 218 | FFN_19 | SwiGLU | 1 × 33792 × 3584 |
| 219 | Add_19_ffn | Add | 1 × 33792 × 3584 |
| 220 | RMSNorm_20_1 | RMSNorm | 1 × 33792 × 3584 |
| 221 | Attention_20 | Grouped Query Attn | 1 × 33792 × 3584 |
| 222 | Add_20_attn | Add | 1 × 33792 × 3584 |
| 223 | RMSNorm_20_2 | RMSNorm | 1 × 33792 × 3584 |
| 224 | FFN_20 | SwiGLU | 1 × 33792 × 3584 |
| 225 | Add_20_ffn | Add | 1 × 33792 × 3584 |
| 226 | RMSNorm_21_1 | RMSNorm | 1 × 33792 × 3584 |
| 227 | Attention_21 | Grouped Query Attn | 1 × 33792 × 3584 |
| 228 | Add_21_attn | Add | 1 × 33792 × 3584 |
| 229 | RMSNorm_21_2 | RMSNorm | 1 × 33792 × 3584 |
| 230 | FFN_21 | SwiGLU | 1 × 33792 × 3584 |
| 231 | Add_21_ffn | Add | 1 × 33792 × 3584 |
| 232 | RMSNorm_22_1 | RMSNorm | 1 × 33792 × 3584 |
| 233 | Attention_22 | Grouped Query Attn | 1 × 33792 × 3584 |
| 234 | Add_22_attn | Add | 1 × 33792 × 3584 |
| 235 | RMSNorm_22_2 | RMSNorm | 1 × 33792 × 3584 |
| 236 | FFN_22 | SwiGLU | 1 × 33792 × 3584 |
| 237 | Add_22_ffn | Add | 1 × 33792 × 3584 |
| 238 | RMSNorm_23_1 | RMSNorm | 1 × 33792 × 3584 |
| 239 | Attention_23 | Grouped Query Attn | 1 × 33792 × 3584 |
| 240 | Add_23_attn | Add | 1 × 33792 × 3584 |
| 241 | RMSNorm_23_2 | RMSNorm | 1 × 33792 × 3584 |
| 242 | FFN_23 | SwiGLU | 1 × 33792 × 3584 |
| 243 | Add_23_ffn | Add | 1 × 33792 × 3584 |
| 244 | RMSNorm_24_1 | RMSNorm | 1 × 33792 × 3584 |
| 245 | Attention_24 | Grouped Query Attn | 1 × 33792 × 3584 |
| 246 | Add_24_attn | Add | 1 × 33792 × 3584 |
| 247 | RMSNorm_24_2 | RMSNorm | 1 × 33792 × 3584 |
| 248 | FFN_24 | SwiGLU | 1 × 33792 × 3584 |
| 249 | Add_24_ffn | Add | 1 × 33792 × 3584 |
| 250 | RMSNorm_25_1 | RMSNorm | 1 × 33792 × 3584 |
| 251 | Attention_25 | Grouped Query Attn | 1 × 33792 × 3584 |
| 252 | Add_25_attn | Add | 1 × 33792 × 3584 |
| 253 | RMSNorm_25_2 | RMSNorm | 1 × 33792 × 3584 |
| 254 | FFN_25 | SwiGLU | 1 × 33792 × 3584 |
| 255 | Add_25_ffn | Add | 1 × 33792 × 3584 |
| 256 | RMSNorm_26_1 | RMSNorm | 1 × 33792 × 3584 |
| 257 | Attention_26 | Grouped Query Attn | 1 × 33792 × 3584 |
| 258 | Add_26_attn | Add | 1 × 33792 × 3584 |
| 259 | RMSNorm_26_2 | RMSNorm | 1 × 33792 × 3584 |
| 260 | FFN_26 | SwiGLU | 1 × 33792 × 3584 |
| 261 | Add_26_ffn | Add | 1 × 33792 × 3584 |
| 262 | RMSNorm_27_1 | RMSNorm | 1 × 33792 × 3584 |
| 263 | Attention_27 | Grouped Query Attn | 1 × 33792 × 3584 |
| 264 | Add_27_attn | Add | 1 × 33792 × 3584 |
| 265 | RMSNorm_27_2 | RMSNorm | 1 × 33792 × 3584 |
| 266 | FFN_27 | SwiGLU | 1 × 33792 × 3584 |
| 267 | Add_27_ffn | Add | 1 × 33792 × 3584 |
| 268 | RMSNorm_28_1 | RMSNorm | 1 × 33792 × 3584 |
| 269 | Attention_28 | Grouped Query Attn | 1 × 33792 × 3584 |
| 270 | Add_28_attn | Add | 1 × 33792 × 3584 |
| 271 | RMSNorm_28_2 | RMSNorm | 1 × 33792 × 3584 |
| 272 | FFN_28 | SwiGLU | 1 × 33792 × 3584 |
| 273 | Add_28_ffn | Add | 1 × 33792 × 3584 |
| 274 | Final_RMSNorm | RMSNorm | 1 × 33792 × 3584 |
| 275 | LM_Head | Linear | 1 × 33792 × 151674 |
| 276 | Output | Output | 1 × 33792 × 151674 |

## Do this to your own model

```
pip install neurarch-trace
neurarch-trace OpenGVLab/InternVL3-8B --plan --share
```

- Page: https://neurarch.com/m/internvl3-8b.html
- All models: https://neurarch.com/m/index.json
- The checks: https://neurarch.com/r/index.json