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.
unsloth/DeepSeek-V3.1-GGUF:IQ1_Sllamacpp · IQ1_S · 179.1 GiB · quantizer (unsloth)
unsloth/DeepSeek-V3.1-GGUF:IQ2_XXSllamacpp · IQ2_XXS · 210.4 GiB · quantizer (unsloth)
unsloth/DeepSeek-V3.1-GGUF:IQ3_XXSllamacpp · IQ3_XXS · 260.5 GiB · quantizer (unsloth)
mlx-community/DeepSeek-V3.1-4bitmlx · 4BIT · 351.7 GiB · quantizer (mlx-community)
unsloth/DeepSeek-V3.1-GGUF:Q4_0llamacpp · Q4_0 · 354.0 GiB · quantizer (unsloth)
QuantTrio/DeepSeek-V3.1-AWQvllm · AWQ · 370.8 GiB · quantizer (QuantTrio)
unsloth/DeepSeek-V3.1-GGUF:Q4_K_Mllamacpp · Q4_K_M · 377.6 GiB · quantizer (unsloth)
mlx-community/DeepSeek-V3.1-8bitmlx · 8BIT · 664.1 GiB · quantizer (mlx-community)
unsloth/DeepSeek-V3.1-GGUF:Q8_0llamacpp · Q8_0 · 664.3 GiB · quantizer (unsloth)
unsloth/DeepSeek-V3.1-GGUF:BF16llamacpp · BF16 · 1250.1 GiB · quantizer (unsloth)