mradermacher/CapRL-Qwen3VL-4B-i1-GGUF

Quantization (fewer layers) vs internlm/CapRL-Qwen3VL-4B. mradermacher/CapRL-Qwen3VL-4B-i1-GGUF matches part of internlm/CapRL-Qwen3VL-4B (399 of its 714 tensors; the rest of internlm/CapRL-Qwen3VL-4B has no counterpart). On the shared part: mradermacher/CapRL-Qwen3VL-4B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 145 tensors match exactly and 254 within quantization error.

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

On the Hub · Downloads on Model Pulse