mradermacher/EditThinker8B-Flux.1-Kontext-Dev-GGUF

Same weights, converted (fewer layers) vs appletea2333/EditThinker8B-Flux.1-Kontext-Dev. mradermacher/EditThinker8B-Flux.1-Kontext-Dev-GGUF matches part of appletea2333/EditThinker8B-Flux.1-Kontext-Dev (399 of its 750 tensors; the rest of appletea2333/EditThinker8B-Flux.1-Kontext-Dev has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

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

On the Hub · Downloads on Model Pulse