Sciguy429/MiMo-V2.5-IK-GGUF overview
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…
Runs locally from ~5.7 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| BF16_IK/MiMo-V2.5-BF16-IK-00001-of-00022.gguf | GGUF | BF16 | 5.7 MB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00002-of-00022.gguf | GGUF | BF16 | 27.24 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00003-of-00022.gguf | GGUF | BF16 | 28.00 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00004-of-00022.gguf | GGUF | BF16 | 28.00 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00005-of-00022.gguf | GGUF | BF16 | 28.00 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00006-of-00022.gguf | GGUF | BF16 | 28.00 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00007-of-00022.gguf | GGUF | BF16 | 28.00 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00008-of-00022.gguf | GGUF | BF16 | 28.00 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00009-of-00022.gguf | GGUF | BF16 | 28.00 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00010-of-00022.gguf | GGUF | BF16 | 28.00 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00011-of-00022.gguf | GGUF | BF16 | 28.00 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00012-of-00022.gguf | GGUF | BF16 | 28.00 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00013-of-00022.gguf | GGUF | BF16 | 28.00 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00014-of-00022.gguf | GGUF | BF16 | 28.00 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00015-of-00022.gguf | GGUF | BF16 | 28.00 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00016-of-00022.gguf | GGUF | BF16 | 28.00 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00017-of-00022.gguf | GGUF | BF16 | 28.00 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00018-of-00022.gguf | GGUF | BF16 | 28.00 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00019-of-00022.gguf | GGUF | BF16 | 28.00 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00020-of-00022.gguf | GGUF | BF16 | 28.00 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00021-of-00022.gguf | GGUF | BF16 | 28.00 GB | Download |
| BF16_IK/MiMo-V2.5-BF16-IK-00022-of-00022.gguf | GGUF | BF16 | 16.00 GB | Download |
| imatrix_BART_BF16.gguf | GGUF | BF16 | 474.8 MB | Download |
| imatrix_UBER_BF16.gguf | GGUF | BF16 | 474.8 MB | Download |
Model Details
Model README
---
base_model:
- XiaomiMiMo/MiMo-V2.5
---
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.
Run Sciguy429/MiMo-V2.5-IK-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models