mlx-community

/

Qwen3-VL-8B-Instruct-4bit

like 5

Follow

MLX Community 8.9k

model.safetensors.index.json seems to be wrong for this model. The model itself only has two safetensors files, but the index expects 4:

    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
    "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
    "model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",

Perhaps the index was copied incorrectly from one of the other quantizations.