DeepSeek V3.1 PRETRAINED

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.

bartowski/deepseek-ai_DeepSeek-V3.1-Base-GGUF:IQ1_Sllamacpp · IQ1_S · 131.6 GiB · quantizer (bartowski)

bartowski/deepseek-ai_DeepSeek-V3.1-Base-GGUF:IQ2_XXSllamacpp · IQ2_XXS · 152.8 GiB · quantizer (bartowski)

bartowski/deepseek-ai_DeepSeek-V3.1-Base-GGUF:IQ3_XXSllamacpp · IQ3_XXS · 249.3 GiB · quantizer (bartowski)

bartowski/deepseek-ai_DeepSeek-V3.1-Base-GGUF:Q4_0llamacpp · Q4_0 · 359.9 GiB · quantizer (bartowski)

bartowski/deepseek-ai_DeepSeek-V3.1-Base-GGUF:Q4_K_Mllamacpp · Q4_K_M · 381.1 GiB · quantizer (bartowski)

deepseek-ai/DeepSeek-V3.1vllm · FP8 · 641.3 GiB · vendor (deepseek-ai)

bartowski/deepseek-ai_DeepSeek-V3.1-Base-GGUF:Q8_0llamacpp · Q8_0 · 664.3 GiB · quantizer (bartowski)

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.

DeepSeek-V3.1-Terminusnot measured DeepSeek-V3.1-Terminusnot measured DeepSeek-V3.1-Terminus-Channel-int8not measured DeepSeek-V3.1-Base-4bitnot measured DeepSeek-V3.1-Terminusnot measured