mradermacher/Qwen2.5-VL-3B-Instruct-Img2Code-i1-GGUF

Quantization (fewer layers) vs Aquiles-ai/Qwen2.5-VL-3B-Instruct-Img2Code. mradermacher/Qwen2.5-VL-3B-Instruct-Img2Code-i1-GGUF matches part of Aquiles-ai/Qwen2.5-VL-3B-Instruct-Img2Code (434 of its 824 tensors; the rest of Aquiles-ai/Qwen2.5-VL-3B-Instruct-Img2Code has no counterpart). On the shared part: mradermacher/Qwen2.5-VL-3B-Instruct-Img2Code-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 181 tensors match exactly and 253 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/252

On the Hub · Downloads on Model Pulse