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.
vcruz305/DeepSeek-V4.1-Flash-GGUF:Q2_Kllamacpp · Q2_K · 246.3 GiB · quantizer (vcruz305)
vcruz305/DeepSeek-V4.1-Flash-GGUF:Q3_K_Mllamacpp · Q3_K_M · 323.4 GiB · quantizer (vcruz305)
hf.co/antirez/deepseek-v4.1-flash-gguf:Q2ollama · Q2 · 340.6 GiB · quantizer (antirez)
vcruz305/DeepSeek-V4.1-Flash-GGUF:Q4_K_Mllamacpp · Q4_K_M · 414.2 GiB · quantizer (vcruz305)
inferencerlabs/DeepSeek-V4.1-Flash-MLX-Q4imlx · BF16 · 434.9 GiB · quantizer (inferencerlabs)
vcruz305/DeepSeek-V4.1-Flash-GGUF:Q8_0llamacpp · Q8_0 · 473.1 GiB · quantizer (vcruz305)
deepseek-ai/DeepSeek-V4.1-Flashvllm · FP8 · 475.3 GiB · vendor (deepseek-ai)