unsloth
/

MiniMax-M2.5-GGUF

Text Generation

Model card Files Files and versions

Resources

View closed (0)

MiniMax-M2.5 GGUF Benchmarks

#6 opened about 2 months ago by

<think> block not generated / requires manual chat template modification

#11 opened 7 days ago by

Q4_K_XL has smaller size than Q4_K_M.

#10 opened 21 days ago by

Q3_K_M - Results with: 2x RTX 2080Ti (22GB VRAM each) // Xeon E5-2682V4 16C 128G DDR4 2133 Quad Channel

#9 opened 28 days ago by

Install & run unsloth/MiniMax-M2.5-GGUF easily using llmpm

#8 opened about 1 month ago by

Any plans to update this model with the new quant formulas?

#7 opened about 1 month ago by

Can you guys do Cerebras' Minimax M2.1 139B REAP?

#5 opened about 2 months ago by

watchingyousleep

can you share ppl graph for your quants ?

#4 opened about 2 months ago by

4-bit quantization: MXFP4_MOE vs Q4_K_XL?

#3 opened about 2 months ago by

Q3_K_XL - Results with: 1x XTX 7900 24GB VRAM // Ryzen 7 9700X 96GB

#2 opened about 2 months ago by

why it's labeled as a finetune

#1 opened about 2 months ago by