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.
hf.co/bartowski/MiniMaxAI_MiniMax-M2-GGUF:IQ1_Sollama · IQ1_S · 43.8 GiB · quantizer (bartowski)
unsloth/MiniMax-M2-GGUF:IQ1_Sllamacpp · IQ1_S · 59.6 GiB · quantizer (unsloth)
unsloth/MiniMax-M2-GGUF:IQ2_XXSllamacpp · IQ2_XXS · 68.9 GiB · quantizer (unsloth)
unsloth/MiniMax-M2-GGUF:IQ3_XXSllamacpp · IQ3_XXS · 87.2 GiB · quantizer (unsloth)
QuantTrio/MiniMax-M2-AWQvllm · AWQ · 112.5 GiB · quantizer (QuantTrio)
lmstudio-community/MiniMax-M2-MLX-4bitmlx · 4BIT · 119.8 GiB · quantizer (lmstudio-community)
unsloth/MiniMax-M2-GGUF:Q4_0llamacpp · Q4_0 · 120.6 GiB · quantizer (unsloth)
unsloth/MiniMax-M2-GGUF:Q4_K_Mllamacpp · Q4_K_M · 128.8 GiB · quantizer (unsloth)
lmstudio-community/MiniMax-M2-MLX-6bitmlx · 6BIT · 173.1 GiB · quantizer (lmstudio-community)
MiniMaxAI/MiniMax-M2vllm · FP8 · 214.3 GiB · vendor (MiniMaxAI)
lmstudio-community/MiniMax-M2-MLX-8bitmlx · 8BIT · 226.3 GiB · quantizer (lmstudio-community)
unsloth/MiniMax-M2-GGUF:Q8_0llamacpp · Q8_0 · 226.4 GiB · quantizer (unsloth)
unsloth/MiniMax-M2-GGUF:BF16llamacpp · BF16 · 426.1 GiB · quantizer (unsloth)