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-M2.7-GGUF:IQ1_Sollama · IQ1_S · 43.5 GiB · quantizer (bartowski)
bartowski/MiniMaxAI_MiniMax-M2.7-GGUF:IQ1_Mllamacpp · IQ1_M · 48.6 GiB · quantizer (bartowski)
bartowski/MiniMaxAI_MiniMax-M2.7-GGUF:IQ2_XXSllamacpp · IQ2_XXS · 56.7 GiB · quantizer (bartowski)
bartowski/MiniMaxAI_MiniMax-M2.7-GGUF:IQ3_XXSllamacpp · IQ3_XXS · 88.6 GiB · quantizer (bartowski)
hf.co/mradermacher/MiniMax-M2.7-GGUF:Q3_K_Sollama · Q3_K_S · 91.9 GiB · quantizer (mradermacher)
hf.co/mradermacher/MiniMax-M2.7-GGUF:Q3_K_Lollama · Q3_K_L · 110.2 GiB · quantizer (mradermacher)
amd/MiniMax-M2.7-MXFP4vllm · QUARK · 118.6 GiB · quantizer (amd)
mlx-community/MiniMax-M2.7-4bitmlx · 4BIT · 119.8 GiB · quantizer (mlx-community)
bartowski/MiniMaxAI_MiniMax-M2.7-GGUF:Q4_0llamacpp · Q4_0 · 120.9 GiB · quantizer (bartowski)
hf.co/mradermacher/MiniMax-M2.7-GGUF:Q4_K_Sollama · Q4_K_S · 121.1 GiB · quantizer (mradermacher)
cyankiwi/MiniMax-M2.7-AWQ-4bitvllm · W4A16 · 121.5 GiB · quantizer (cyankiwi)
lukealonso/MiniMax-M2.7-NVFP4vllm · NVFP4 · 125.3 GiB · quantizer (lukealonso)
hf.co/mradermacher/MiniMax-M2.7-GGUF:Q4_K_Mollama · Q4_K_M · 128.8 GiB · quantizer (mradermacher)
bartowski/MiniMaxAI_MiniMax-M2.7-GGUF:Q4_K_Mllamacpp · Q4_K_M · 129.3 GiB · quantizer (bartowski)
MiniMaxAI/MiniMax-M2.7vllm · FP8 · 214.3 GiB · vendor (MiniMaxAI)
bartowski/MiniMaxAI_MiniMax-M2.7-GGUF:Q8_0llamacpp · Q8_0 · 226.4 GiB · quantizer (bartowski)
unsloth/MiniMax-M2.7-GGUF:BF16llamacpp · BF16 · 426.1 GiB · quantizer (unsloth)