Downloads · 30 days
41
4% of all-time downloads
MiMo-V2.5-IK-GGUF
Sciguy429/MiMo-V2.5-IK-GGUF
MiMo-V2.5-IK-GGUF is a machine learning model from Sciguy429. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
961
Public
Repo size
665 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.gguf619 GB · 93%
At a glance
- Access
- Public
- Created
- Jul 13, 2026
- Updated
- Jul 14, 2026
- SHA
- 4b9d23ee
Base models
Model card
From the Hugging Face model README
WIP ik_llama quants for MiMo-V2.5
This is a set of not QKV merged quants for MiMo-V2.5, compatible with mainline ik_llama.cpp.
Context:
Mainline lama.cpp opted to go against the base MiMo-V2.5 files and fuse the model's Q, K and V tensors together in this PR. This poses no functional issues, but completely broke already existing support from ik_llama. Since this change every mainline quant has had these fused tensors, making it essentially impossible to run MiMo-V2.5 on ik_llama without doing everything yourself. Worst still, this makes existing imatrix files equally incompatible.
Currently this repo just has the base converted BF16 tensors, two generated imatrix sets (one with Ubergram's corpus and the other made form Bartowski's), and a BF16 logits file generated at 512 ctx and a batch size of 2048.
- Created
- Jul 13, 2026
- Updated
- Jul 14, 2026