aessedai/minimax-m2.7-gguf - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.
Model Intelligence Sheet
aessedai/minimax-m2.7-gguf overview
Notes
Downloads
2,756
Likes
18
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
21 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| MiniMax-M2.7-IQ3_S-00001-of-00003.gguf | GGUF | IQ3_S | 7.86 MB | Download |
| MiniMax-M2.7-IQ3_S-00002-of-00003.gguf | GGUF | IQ3_S | 46.49 GB | Download |
| MiniMax-M2.7-IQ3_S-00003-of-00003.gguf | GGUF | IQ3_S | 31.38 GB | Download |
| MiniMax-M2.7-IQ4_XS-00001-of-00004.gguf | GGUF | IQ4_XS | 7.86 MB | Download |
| MiniMax-M2.7-IQ4_XS-00002-of-00004.gguf | GGUF | IQ4_XS | 46.37 GB | Download |
| MiniMax-M2.7-IQ4_XS-00003-of-00004.gguf | GGUF | IQ4_XS | 46.19 GB | Download |
| MiniMax-M2.7-IQ4_XS-00004-of-00004.gguf | GGUF | IQ4_XS | 8.54 GB | Download |
| MiniMax-M2.7-Q4_K_M-00001-of-00004.gguf | GGUF | Q4_K_M | 7.86 MB | Download |
| MiniMax-M2.7-Q4_K_M-00002-of-00004.gguf | GGUF | Q4_K_M | 46.47 GB | Download |
| MiniMax-M2.7-Q4_K_M-00003-of-00004.gguf | GGUF | Q4_K_M | 46.56 GB | Download |
| MiniMax-M2.7-Q4_K_M-00004-of-00004.gguf | GGUF | Q4_K_M | 37.65 GB | Download |
| MiniMax-M2.7-Q4_K_S-00001-of-00004.gguf | GGUF | Q4_K_S | 7.86 MB | Download |
| MiniMax-M2.7-Q4_K_S-00002-of-00004.gguf | GGUF | Q4_K_S | 46.25 GB | Download |
| MiniMax-M2.7-Q4_K_S-00003-of-00004.gguf | GGUF | Q4_K_S | 46.23 GB | Download |
| MiniMax-M2.7-Q4_K_S-00004-of-00004.gguf | GGUF | Q4_K_S | 25.26 GB | Download |
| MiniMax-M2.7-Q5_K_M-00001-of-00005.gguf | GGUF | Q5_K_M | 7.86 MB | Download |
| MiniMax-M2.7-Q5_K_M-00002-of-00005.gguf | GGUF | Q5_K_M | 46.55 GB | Download |
| MiniMax-M2.7-Q5_K_M-00003-of-00005.gguf | GGUF | Q5_K_M | 46.22 GB | Download |
| MiniMax-M2.7-Q5_K_M-00004-of-00005.gguf | GGUF | Q5_K_M | 46.07 GB | Download |
| MiniMax-M2.7-Q5_K_M-00005-of-00005.gguf | GGUF | Q5_K_M | 18.39 GB | Download |
| imatrix.gguf | GGUF | — | 469.61 MB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"base_model": [
"MiniMaxAI/MiniMax-M2.7"
],
"frontmatter": {
"base_model": [
"MiniMaxAI/MiniMax-M2.7"
]
},
"hero_image_url": "kld_data/01_kld_vs_filesize.png \"Chart showing Pareto KLD analysis of quants\"",
"summary": "## Notes",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nbase_model:\n- MiniMaxAI/MiniMax-M2.7\n---\n## Notes\n- 04-15-2026: I've uploaded a working Q4_K_M using the findings from Unsloth regarding the blk.61.ffn_down_exps causing the `nan` issue, for the Q4_K_M I've quantized that specific tensor to Q6_K.\n- 04-12-2026: The Q4_K_M I uploaded seems to have some issues, the PPL / KLD was throwing `nan` so I'll remove the model for now and try to get a working quant up tomorrow.\n\n## Description\nThis repo contains specialized MoE-quants for MiniMax-M2.7. The idea being that given the huge size of the FFN tensors compared to the rest of the tensors in the model, \nit should be possible to achieve a better quality while keeping the overall size of the entire model smaller compared to a similar naive quantization. \nTo that end, the quantization type default is kept in high quality and the FFN UP + FFN GATE tensors are quanted down along with the FFN DOWN tensors.\n\n| Quant | Size | Mixture | PPL | 1-(Mean PPL(Q)/PPL(base)) | KLD |\n| :--------- | :--------- | :------- | :------- | :------- | :------- |\n| Q8_0 | 226.43 GiB (8.51 BPW) | Q8_0 | 7.880138 ± 0.060034 | +0.2412% | 0.029715 ± 0.000649 |\n| Q5_K_M | 157.23 GiB (5.91 BPW) | Q8_0 / Q5_K / Q5_K / Q6_K | 7.871878 ± 0.059897 | +0.1361% | 0.038926 ± 0.000692 |\n| Q4_K_M | 130.67 GiB (4.91 BPW) | Q8_0 / Q4_K / Q4_K / Q5_K | 7.951215 ± 0.060706 | +1.1453% | 0.059323 ± 0.000771 |\n| Q4_K_S | 117.74 GiB (4.42 BPW) | Q8_0 / IQ4_XS / IQ4_XS / Q4_K | 7.968221 ± 0.060797 | +1.3616% | 0.071012 ± 0.000774 |\n| IQ4_XS | 101.10 GiB (3.80 BPW) | Q8_0 / IQ3_S / IQ3_S / IQ4_XS | 8.290674 ± 0.063543 | +5.4635% | 0.128807 ± 0.001070 |\n| IQ3_S | 77.86 GiB (2.92 BPW) | Q6_K / IQ2_S / IQ2_S / IQ3_S | 8.815764 ± 0.067859 | +12.1430% | 0.282740 ± 0.001687 |\n\n\n![kld_graph](kld_data/01_kld_vs_filesize.png \"Chart showing Pareto KLD analysis of quants\")\n![ppl_graph](kld_data/02_ppl_vs_filesize.png \"Chart showing Pareto PPL analysis of quants\")",
"related_quantizations": []
},
"tags": [
"gguf",
"base_model:MiniMaxAI/MiniMax-M2.7",
"base_model:quantized:MiniMaxAI/MiniMax-M2.7",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
],
"likes": 18,
"downloads": 2756,
"gated": false,
"private": false,
"last_modified": "2026-04-16T08:56:04.000Z",
"created_at": "2026-04-12T07:15:32.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "69db46942ad44b2e0638e319",
"id": "AesSedai/MiniMax-M2.7-GGUF",
"modelId": "AesSedai/MiniMax-M2.7-GGUF",
"sha": "919b832d7d38bd7fbd8ceea4d4443cc9d75eda1c",
"createdAt": "2026-04-12T07:15:32.000Z",
"lastModified": "2026-04-16T08:56:04.000Z",
"author": "AesSedai",
"downloads": 2756,
"likes": 18,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 32
}