Downloads · 30 days
647
3% of all-time downloads
MiniMax-M2-THRIFT-55-i1-GGUF
mradermacher/MiniMax-M2-THRIFT-55-i1-GGUF
MiniMax-M2-THRIFT-55-i1-GGUF is a machine learning model from mradermacher. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
weighted/imatrix quants of https://huggingface.co/lemuralabs/MiniMax-M2-Pruned-55
All-time downloads
23.3K
Public
Repo size
1.1 TB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.gguf469 GB · 42%
At a glance
- Library
- transformers
- License
- mit
- Access
- Public
- Created
- Nov 26, 2025
- Updated
- Aug 17, 2026
- SHA
- 461b2fd8
Base models
Model card
From the Hugging Face model README
About
<!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> <!-- ### quants: Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: -->weighted/imatrix quants of https://huggingface.co/lemuralabs/MiniMax-M2-Pruned-55
<!-- provided-files -->For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/MiniMax-M2-THRIFT-55-GGUF
Usage
If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.
Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| GGUF | imatrix | 0.3 | imatrix file (for creating your own quants) |
| GGUF | i1-IQ1_S | 21.9 | for the desperate |
| GGUF | i1-IQ1_M | 24.2 | mostly desperate |
| GGUF | i1-IQ2_XXS | 28.1 | |
| GGUF | i1-IQ2_XS | 31.2 | |
| GGUF | i1-IQ2_S | 31.9 | |
| GGUF | i1-IQ2_M | 35.0 | |
| GGUF | i1-Q2_K_S | 36.2 | very low quality |
| GGUF | i1-Q2_K | 38.8 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 40.9 | lower quality |
| GGUF | i1-IQ3_XS | 43.4 | |
| GGUF | i1-Q3_K_S | 45.9 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 45.9 | beats Q3_K* |
| GGUF | i1-IQ3_M | 46.6 | |
| PART 1 PART 2 | i1-Q3_K_M | 50.8 | IQ3_S probably better |
| PART 1 PART 2 | i1-Q3_K_L | 55.0 | IQ3_M probably better |
| PART 1 PART 2 | i1-IQ4_XS | 56.6 | |
| PART 1 PART 2 | i1-Q4_0 | 60.1 | fast, low quality |
| PART 1 PART 2 | i1-Q4_K_S | 60.3 | optimal size/speed/quality |
| PART 1 PART 2 | i1-Q4_K_M | 64.1 | fast, recommended |
| PART 1 PART 2 | i1-Q4_1 | 66.4 | |
| PART 1 PART 2 | i1-Q5_K_S | 73.0 | |
| PART 1 PART 2 | i1-Q5_K_M | 75.2 | |
| PART 1 PART 2 | i1-Q6_K | 87.0 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.
Thanks
I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->- Library
- transformers
- License
- mit
- Languages
- en
- Created
- Nov 26, 2025
- Updated
- Aug 17, 2026