GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

eugene-kamenev/GRM-3.2-Sky-Q4_K_M-GGUF overview

Quantized using no mtp flag, Tested the inference does work using latest llama.cpp with vision support.

ggufllama-cppimage-text-to-textbase_model:OrionLLM/GRM-3.2-Skybase_model:quantized:OrionLLM/GRM-3.2-Skylicense:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~857.6 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
137
Likes
0
Pipeline
image-text-to-text

Repository Files & Downloads

5 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
grm-3.2-sky-apex-balanced.ggufGGUFGGUF23.60 GBDownload
grm-3.2-sky-apex-compact.ggufGGUFGGUF15.53 GBDownload
grm-3.2-sky-apex-quality.ggufGGUFGGUF21.25 GBDownload
grm-3.2-sky-q4_k_m.ggufGGUFQ4_K_M19.71 GBDownload
mmproj-model-f16.ggufGGUFF16857.6 MBDownload

Model Details

Model IDeugene-kamenev/GRM-3.2-Sky-Q4_K_M-GGUF
Authoreugene-kamenev
Pipelineimage-text-to-text
Licenseapache-2.0
Base modelOrionLLM/GRM-3.2-Sky
Last modified2026-08-02T02:58:40.000Z

Model README

---

license: apache-2.0

base_model: OrionLLM/GRM-3.2-Sky

pipeline_tag: image-text-to-text

tags:

- llama-cpp

---

Quantized using --no-mtp flag,

Tested the inference does work using latest llama.cpp with vision support.

Run eugene-kamenev/GRM-3.2-Sky-Q4_K_M-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models