Downloads · 30 days
270
4% of all-time downloads
MiniMax-M2.5-GGUF
QuantPasture/MiniMax-M2.5-GGUF
MiniMax-M2.5-GGUF is a machine learning model from QuantPasture. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This repo contains specialized MoE-quants for MiniMax-M2.5. The idea being that given the huge size of the FFN tensors compared to the rest of the tensors in the model, it should be possible to achieve a better qualit…
All-time downloads
6.4K
Public
Repo size
503 GB
Likes
30
Public
Repo makeup
Click a slice to open those files.
.gguf503 GB · 100%
At a glance
- Access
- Public
- Created
- Feb 14, 2026
- Updated
- May 1, 2026
- SHA
- 71707d42
Base models
Model card
From the Hugging Face model README
This repo contains specialized MoE-quants for MiniMax-M2.5. The idea being that given the huge size of the FFN tensors compared to the rest of the tensors in the model, it should be possible to achieve a better quality while keeping the overall size of the entire model smaller compared to a similar naive quantization. To 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.
| Quant | Size | Mixture | PPL | 1-(Mean PPL(Q)/PPL(base)) | KLD |
|---|---|---|---|---|---|
| Q5_K_M | 157.23 GiB (5.91 BPW) | Q8_0 / Q5_K / Q5_K / Q6_K | 7.126261 ± 0.115850 | +0.5877% | 0.023465 ± 0.001079 |
| Q4_K_M | 130.52 GiB (4.90 BPW) | Q8_0 / Q4_K / Q4_K / Q5_K | 7.173459 ± 0.116673 | +1.2462% | 0.041269 ± 0.001426 |
| IQ4_XS | 101.10 GiB (3.80 BPW) | Q8_0 / IQ3_S / IQ3_S / IQ4_XS | 7.513587 ± 0.122746 | +6.0549% | 0.095077 ± 0.002168 |
| IQ3_S | 78.76 GiB (2.96 BPW) | Q8_0 / IQ2_S / IQ2_S / IQ3_S | 8.284882 ± 0.135705 | +16.9418% | 0.244096 ± 0.004148 |
Provided here as well as a couple of graphs showing the Pareto frontier for KLD and PPL for my quants vs Unsloth.
Full graphs of all of the quants are available in the kld_data directory, as well as the raw data broken down per quant as well as a CSV with the collated data.
While the PPL between the quant methods is similar, I feel like the KLD of the quants provided here are slightly better and that these quants will offer better long context performance due to keeping the default type as Q8_0. This comes with a slight performance penalty in PP / TG due to the higher quality quantization but I think the tradeoff is worthwhile.
- Created
- Feb 14, 2026
- Updated
- May 1, 2026