mradermacher/Eden-Qwen3-VL-4B-Instruct-BF16-v1-GGUF

Same weights, converted (fewer layers) vs eden-suite/Eden-Qwen3-VL-4B-Instruct-BF16-v1. mradermacher/Eden-Qwen3-VL-4B-Instruct-BF16-v1-GGUF matches part of eden-suite/Eden-Qwen3-VL-4B-Instruct-BF16-v1 (398 of its 713 tensors; the rest of eden-suite/Eden-Qwen3-VL-4B-Instruct-BF16-v1 has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144

On the Hub · Downloads on Model Pulse