Model Intelligence Sheet
gszj2018/MiMo-V2.6-Flash-MOPD-Strix-Halo-GGUF overview
Mixed precision quantized MiMo V2.6 Flash MOPD for Strix Halo Requirement One 128GB Strix Halo machine AMD Ryzen AI Max+ 395, gfx1151 llama.cpp v0.5.0 or later…
Runs locally from ~2.56 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | gszj2018/MiMo-V2.6-Flash-MOPD-Strix-Halo-GGUF |
|---|---|
| Author | gszj2018 |
| Pipeline | image-text-to-text |
| License | mit |
| Base model | XiaomiMiMo/MiMo-V2.6-Flash-MOPD |
| Last modified | 2026-10-13T18:28:09.000Z |
Model README
---
license: mit
base_model:
- XiaomiMiMo/MiMo-V2.6-Flash-MOPD
base_model_relation: quantized
pipeline_tag: image-text-to-text
tags:
- strix-halo
- gfx1151
- quantized
- mimo
---
Mixed-precision quantized MiMo-V2.6-Flash-MOPD for Strix Halo
Requirement
- One 128GB Strix Halo machine (AMD Ryzen AI Max+ 395, gfx1151)
llama.cppv0.5.0or later
Example command
/path/to/build/bin/llama-server --host 0.0.0.0 --port 9931 \
-m /path/to/model.gguf --mmproj /path/to/mmproj.gguf \
-c 128000 -n 64000 -dev Vulkan0 \
--reasoning on --temp 1.0 --top-p 0.95 Run gszj2018/MiMo-V2.6-Flash-MOPD-Strix-Halo-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models