Files and memory at 8K context
| Quant | File | Files | + KV + runtime | Smallest fit | Source |
|---|---|---|---|---|---|
| Q4_K_M bartowski/MiniMaxAI_MiniMax-M2.7-GGUF | 129 GiB | 4 | 132 GiB+ | 192 GB GPU | HF files |
| Q5_K_M bartowski/MiniMaxAI_MiniMax-M2.7-GGUF | 151 GiB | 5 | 154 GiB+ | 192 GB GPU | HF files |
| Q8_0 unsloth/MiniMax-M2.7-GGUF | 226 GiB | 6 | 229 GiB+ | over 192 GB GPU | HF files |
| BF16 unsloth/MiniMax-M2.7-GGUF | 426 GiB | 10 | 429 GiB+ | over 192 GB GPU | HF files |
| MLX 4-bit mixed precision mlx-community/MiniMax-M2.7-4bit | 120 GiB | 27 | 123 GiB+ | 192 GB Mac | HF files |
| MLX 8-bit mixed precision mlx-community/MiniMax-M2.7-8bit | 226 GiB | 47 | 229 GiB+ | 512 GB Mac | HF files |
No verified file: FP16. Sizes are exact file bytes (text weights; projectors listed separately). “+” = recurrent state or other terms unknown. Smallest fit adds 0.5 GiB spare; Macs use 75% of memory.
Quality
Artificial Analysis Intelligence Index
Unknown
Arena text rating
Unknown
Scores describe the evaluated hosted variant, not each quantized file. AA and Arena are never averaged.
Reported speeds 0
No reported measurement yet. Submit one.