avar6/Motif-3-Beta-gguf overview
These are experimental ggufs for Motif 3 beta. They require this llamacpp fork https://github.com/ggml org/llama.cpp/pull/26298 UPDATE: These will most likely …
Runs locally from ~7.27 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Q2_K.v3/Motif3-Q2_K.v3.gguf-00001-of-00003.gguf | GGUF | Q2_K | 46.26 GB | Download |
| Q2_K.v3/Motif3-Q2_K.v3.gguf-00002-of-00003.gguf | GGUF | Q2_K | 45.97 GB | Download |
| Q2_K.v3/Motif3-Q2_K.v3.gguf-00003-of-00003.gguf | GGUF | Q2_K | 20.95 GB | Download |
| Q3_K_M.v3/Motif3-Q3_K_M.v3.gguf-00001-of-00004.gguf | GGUF | Q3_K_M | 46.14 GB | Download |
| Q3_K_M.v3/Motif3-Q3_K_M.v3.gguf-00002-of-00004.gguf | GGUF | Q3_K_M | 46.05 GB | Download |
| Q3_K_M.v3/Motif3-Q3_K_M.v3.gguf-00003-of-00004.gguf | GGUF | Q3_K_M | 46.16 GB | Download |
| Q3_K_M.v3/Motif3-Q3_K_M.v3.gguf-00004-of-00004.gguf | GGUF | Q3_K_M | 7.27 GB | Download |
| Q4_K_M.v3/Motif3-Q4_K_M.v3.gguf-00001-of-00004.gguf | GGUF | Q4_K_M | 46.11 GB | Download |
| Q4_K_M.v3/Motif3-Q4_K_M.v3.gguf-00002-of-00004.gguf | GGUF | Q4_K_M | 46.12 GB | Download |
| Q4_K_M.v3/Motif3-Q4_K_M.v3.gguf-00003-of-00004.gguf | GGUF | Q4_K_M | 46.25 GB | Download |
| Q4_K_M.v3/Motif3-Q4_K_M.v3.gguf-00004-of-00004.gguf | GGUF | Q4_K_M | 44.03 GB | Download |
| Q5_K_M.v3/Motif3-Q5_K_M.v3.gguf-00001-of-00005.gguf | GGUF | Q5_K_M | 46.26 GB | Download |
| Q5_K_M.v3/Motif3-Q5_K_M.v3.gguf-00002-of-00005.gguf | GGUF | Q5_K_M | 46.54 GB | Download |
| Q5_K_M.v3/Motif3-Q5_K_M.v3.gguf-00003-of-00005.gguf | GGUF | Q5_K_M | 45.07 GB | Download |
| Q5_K_M.v3/Motif3-Q5_K_M.v3.gguf-00004-of-00005.gguf | GGUF | Q5_K_M | 45.22 GB | Download |
| Q5_K_M.v3/Motif3-Q5_K_M.v3.gguf-00005-of-00005.gguf | GGUF | Q5_K_M | 29.76 GB | Download |
Model Details
Model README
---
base_model:
- Motif-Technologies/Motif-3-Beta
tags:
- gguf
- Llamacpp
---
These are experimental ggufs for Motif 3 beta. They require this llamacpp fork https://github.com/ggml-org/llama.cpp/pull/26298
UPDATE: These will most likely need to be requanted. Though they work excellently at the moment, the update should improve them further. When they are updated they will be labeled v2.
UPDATE UPDATE: all v2 versions are now uploaded.
UPDATE V3: new v3 versions of the ggufs have been uploaded. These should have faster prompt processing and smaller kvcache
Run avar6/Motif-3-Beta-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models