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/Kimi-K2-Instruct-0905-GGUF:IQ1_Sllamacpp · IQ1_S · 262.5 GiB · quantizer (unsloth)
unsloth/Kimi-K2-Instruct-0905-GGUF:IQ2_XXSllamacpp · IQ2_XXS · 308.1 GiB · quantizer (unsloth)
unsloth/Kimi-K2-Instruct-0905-GGUF:IQ3_XXSllamacpp · IQ3_XXS · 388.6 GiB · quantizer (unsloth)
amd/Kimi-K2-Instruct-0905-MXFP4vllm · QUARK · 520.3 GiB · quantizer (amd)
richardyoung/Kimi-K2-Instruct-0905-MLX-4bitmlx · 4BIT · 537.9 GiB · quantizer (richardyoung)
unsloth/Kimi-K2-Instruct-0905-GGUF:Q4_0llamacpp · Q4_0 · 541.3 GiB · quantizer (unsloth)
unsloth/Kimi-K2-Instruct-0905-GGUF:Q4_K_Mllamacpp · Q4_K_M · 578.6 GiB · quantizer (unsloth)
richardyoung/Kimi-K2-Instruct-0905-MLX-6bitmlx · 6BIT · 776.9 GiB · quantizer (richardyoung)
moonshotai/Kimi-K2-Instruct-0905vllm · FP8 · 958.5 GiB · vendor (moonshotai)
richardyoung/Kimi-K2-Instruct-0905-MLX-8bitmlx · 8BIT · 1015.8 GiB · quantizer (richardyoung)
unsloth/Kimi-K2-Instruct-0905-GGUF:Q8_0llamacpp · Q8_0 · 1016.1 GiB · quantizer (unsloth)
unsloth/Kimi-K2-Instruct-0905-GGUF:BF16llamacpp · BF16 · 1912.1 GiB · quantizer (unsloth)