← DeepSeek V4

DeepSeek V4 FLASH-0731

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-V4-Flash-0731-GGUF:IQ1_Sllamacpp · IQ1_S · 76.9 GiB · quantizer (unsloth)
unsloth/DeepSeek-V4-Flash-0731-GGUF:IQ2_XXSllamacpp · IQ2_XXS · 84.6 GiB · quantizer (unsloth)
unsloth/DeepSeek-V4-Flash-0731-GGUF:IQ3_XXSllamacpp · IQ3_XXS · 97.1 GiB · quantizer (unsloth)
unsloth/DeepSeek-V4-Flash-0731-GGUF:Q4_K_XLllamacpp · Q4_K_XL · 144.4 GiB · quantizer (unsloth)
deepseek-ai/DeepSeek-V4-Flash-0731vllm · FP8 · 155.4 GiB · vendor (deepseek-ai)
TensorFold/DeepSeek-V4-Flash-0731-MXFP4-MLXmlx · 4BIT · 155.6 GiB · quantizer (TensorFold)