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/MiMo-V2-Flash-GGUF:IQ1_Sllamacpp · IQ1_S · 81.2 GiB · quantizer (unsloth)
unsloth/MiMo-V2-Flash-GGUF:IQ2_XXSllamacpp · IQ2_XXS · 94.6 GiB · quantizer (unsloth)
hf.co/mradermacher/MiMo-V2-Flash-GGUF:Q2_Kollama · Q2_K · 104.6 GiB · quantizer (mradermacher)
unsloth/MiMo-V2-Flash-GGUF:IQ3_XXSllamacpp · IQ3_XXS · 118.7 GiB · quantizer (unsloth)
hf.co/mradermacher/MiMo-V2-Flash-GGUF:Q3_K_Sollama · Q3_K_S · 124.0 GiB · quantizer (mradermacher)
hf.co/mradermacher/MiMo-V2-Flash-GGUF:Q3_K_Lollama · Q3_K_L · 148.6 GiB · quantizer (mradermacher)
mlx-community/MiMo-V2-Flash-4bitmlx · 4BIT · 161.8 GiB · quantizer (mlx-community)
unsloth/MiMo-V2-Flash-GGUF:Q4_0llamacpp · Q4_0 · 162.7 GiB · quantizer (unsloth)
hf.co/mradermacher/MiMo-V2-Flash-GGUF:Q4_K_Sollama · Q4_K_S · 163.3 GiB · quantizer (mradermacher)
unsloth/MiMo-V2-Flash-GGUF:Q4_K_Mllamacpp · Q4_K_M · 174.0 GiB · quantizer (unsloth)
hf.co/mradermacher/MiMo-V2-Flash-GGUF:Q4_K_Mollama · Q4_K_M · 174.0 GiB · quantizer (mradermacher)
XiaomiMiMo/MiMo-V2-Flashvllm · FP8 · 291.6 GiB · vendor (XiaomiMiMo)
unsloth/MiMo-V2-Flash-GGUF:Q8_0llamacpp · Q8_0 · 305.7 GiB · quantizer (unsloth)
unsloth/MiMo-V2-Flash-GGUF:BF16llamacpp · BF16 · 575.2 GiB · quantizer (unsloth)