Model Intelligence Sheet
avar6/Motif-3-gguf overview
Experimental ggufs of the final version of Motif 3. As with the beta ggufs, they require this llamacpp fork https://github.com/ggml org/llama.cpp/pull/26298 No…
Runs locally from ~7.27 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
22 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Motif3-Q5_K_M.gguf-00001-of-00005.gguf | GGUF | Q5_K_M | 46.26 GB | Download |
| Motif3-Q5_K_M.gguf-00002-of-00005.gguf | GGUF | Q5_K_M | 46.54 GB | Download |
| Motif3-Q5_K_M.gguf-00003-of-00005.gguf | GGUF | Q5_K_M | 45.07 GB | Download |
| Motif3-Q5_K_M.gguf-00004-of-00005.gguf | GGUF | Q5_K_M | 45.22 GB | Download |
| Motif3-Q5_K_M.gguf-00005-of-00005.gguf | GGUF | Q5_K_M | 29.76 GB | Download |
| Q3_K_M-mixed/Motif3-Q3_K_M-mixed-00001-of-00003.gguf | GGUF | Q3_K_M | 46.23 GB | Download |
| Q3_K_M-mixed/Motif3-Q3_K_M-mixed-00002-of-00003.gguf | GGUF | Q3_K_M | 46.19 GB | Download |
| Q3_K_M-mixed/Motif3-Q3_K_M-mixed-00003-of-00003.gguf | GGUF | Q3_K_M | 40.12 GB | Download |
| Q3_K_M/Motif3-Q3_K_M.gguf-00001-of-00004.gguf | GGUF | Q3_K_M | 46.14 GB | Download |
| Q3_K_M/Motif3-Q3_K_M.gguf-00002-of-00004.gguf | GGUF | Q3_K_M | 46.05 GB | Download |
| Q3_K_M/Motif3-Q3_K_M.gguf-00003-of-00004.gguf | GGUF | Q3_K_M | 46.16 GB | Download |
| Q3_K_M/Motif3-Q3_K_M.gguf-00004-of-00004.gguf | GGUF | Q3_K_M | 7.27 GB | Download |
| Q4_K_M/Motif3-Q4_K_M.gguf-00001-of-00004.gguf | GGUF | Q4_K_M | 46.11 GB | Download |
| Q4_K_M/Motif3-Q4_K_M.gguf-00002-of-00004.gguf | GGUF | Q4_K_M | 46.12 GB | Download |
| Q4_K_M/Motif3-Q4_K_M.gguf-00003-of-00004.gguf | GGUF | Q4_K_M | 46.25 GB | Download |
| Q4_K_M/Motif3-Q4_K_M.gguf-00004-of-00004.gguf | GGUF | Q4_K_M | 44.03 GB | Download |
| Q6_K/Motif3-Q6_K.gguf-00001-of-00006.gguf | GGUF | Q6_K | 46.53 GB | Download |
| Q6_K/Motif3-Q6_K.gguf-00002-of-00006.gguf | GGUF | Q6_K | 46.13 GB | Download |
| Q6_K/Motif3-Q6_K.gguf-00003-of-00006.gguf | GGUF | Q6_K | 46.00 GB | Download |
| Q6_K/Motif3-Q6_K.gguf-00004-of-00006.gguf | GGUF | Q6_K | 46.12 GB | Download |
| Q6_K/Motif3-Q6_K.gguf-00005-of-00006.gguf | GGUF | Q6_K | 46.13 GB | Download |
| Q6_K/Motif3-Q6_K.gguf-00006-of-00006.gguf | GGUF | Q6_K | 14.17 GB | Download |
Model Details
Model README
---
base_model:
- Motif-Technologies/Motif-3
---
Experimental ggufs of the final version of Motif-3. As with the beta ggufs, they require this llamacpp fork https://github.com/ggml-org/llama.cpp/pull/26298
Note: I am running out of space my huggingface and may have to delete some of the beta ggufs to make room for the final ones. As of right now, uploading Q3, Q4, Q5, and Q6 final ggufs
Run avar6/Motif-3-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models