DevQuasar/amd.Instella-MoE-16B-A3B-Think-GGUF overview
<img src="https://raw.githubusercontent.com/csabakecskemeti/devquasar/main/dq logo black transparent.png" width="200"/ https://devquasar.com 'Make knowledge fr…
Runs locally from ~6.07 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Q2_K/amd.Instella-MoE-16B-A3B-Think.f16.gguf.Q2_K.gguf | GGUF | Q2_K | 6.07 GB | Download |
| Q3_K_M/amd.Instella-MoE-16B-A3B-Think.f16.gguf.Q3_K_M.gguf | GGUF | Q3_K_M | 7.65 GB | Download |
| Q4_K_M/amd.Instella-MoE-16B-A3B-Think.f16.gguf.Q4_K_M.gguf | GGUF | Q4_K_M | 9.75 GB | Download |
| Q5_K_M/amd.Instella-MoE-16B-A3B-Think.f16.gguf.Q5_K_M.gguf | GGUF | Q5_K_M | 11.15 GB | Download |
| Q6_K/amd.Instella-MoE-16B-A3B-Think.f16.gguf.Q6_K.gguf | GGUF | Q6_K | 13.23 GB | Download |
| Q8_0/amd.Instella-MoE-16B-A3B-Think.f16.gguf.Q8_0.gguf | GGUF | Q8_0 | 15.71 GB | Download |
Model Details
| Model ID | DevQuasar/amd.Instella-MoE-16B-A3B-Think-GGUF |
|---|---|
| Author | DevQuasar |
| Pipeline | text-generation |
| License | — |
| Base model | amd/Instella-MoE-16B-A3B-Think |
| Last modified | 2026-07-31T23:01:23.000Z |
Model README
---
base_model:
- amd/Instella-MoE-16B-A3B-Think
pipeline_tag: text-generation
---
'Make knowledge free for everyone'
Experimental
Use this llama.cpp branch: https://github.com/csabakecskemeti/llama.cpp/tree/instella-moe
Quantized version of: amd/Instella-MoE-16B-A3B-Think
<a href='https://ko-fi.com/L4L416YX7C' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi6.png?v=6' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>
Run DevQuasar/amd.Instella-MoE-16B-A3B-Think-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models