← DeepSeek V3.2

DeepSeek V3.2 SPECIALE

No machine on this network has measured this model yet. Everything below is what the catalog knows exists — where the weights come from, how large each build is, and whose work it is. Nothing here is a claim about what the model can do; that only appears once a machine has run it and signed the result.

ubergarm/DeepSeek-V3.2-Speciale-GGUF:IQ1_KTllamacpp · IQ1_KT · 146.2 GiB · quantizer (ubergarm)
deepseek-ai/DeepSeek-V3.2-Specialevllm · FP8 · 642.1 GiB · vendor (deepseek-ai)
derivatives — somebody else's change to these weights

Fine-tunes, merges and abliterations of this member, each its own model with its own page. None of their numbers are counted above.