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

mrutkows/granite-5.0-120b-sft-GGUF overview

granite 5.0 120b sft GGUF NOTE This repository contains models that have been converted to the GGUF format with various quantizations from an IBM Granite base …

llama.cppgguflanguagegranite-5.0base_model:ibm-research/granite-5.0-120b-sftbase_model:quantized:ibm-research/granite-5.0-120b-sftlicense:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~7.00 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
286
Likes
0
Pipeline
Author

Repository Files & Downloads

13 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
granite-5.0-120b-sft-Q4_K_M-00001-of-00002.ggufGGUFQ4_K_M41.52 GBDownload
granite-5.0-120b-sft-Q4_K_M-00002-of-00002.ggufGGUFQ4_K_M25.12 GBDownload
granite-5.0-120b-sft-Q5_K_M-00001-of-00002.ggufGGUFQ5_K_M41.62 GBDownload
granite-5.0-120b-sft-Q5_K_M-00002-of-00002.ggufGGUFQ5_K_M36.46 GBDownload
granite-5.0-120b-sft-Q6_K-00001-of-00003.ggufGGUFQ6_K41.63 GBDownload
granite-5.0-120b-sft-Q6_K-00002-of-00003.ggufGGUFQ6_K41.62 GBDownload
granite-5.0-120b-sft-Q6_K-00003-of-00003.ggufGGUFQ6_K7.00 GBDownload
granite-5.0-120b-sft-bf16-00001-of-00006.ggufGGUFBF1640.99 GBDownload
granite-5.0-120b-sft-bf16-00002-of-00006.ggufGGUFBF1641.01 GBDownload
granite-5.0-120b-sft-bf16-00003-of-00006.ggufGGUFBF1641.01 GBDownload
granite-5.0-120b-sft-bf16-00004-of-00006.ggufGGUFBF1641.01 GBDownload
granite-5.0-120b-sft-bf16-00005-of-00006.ggufGGUFBF1641.01 GBDownload
granite-5.0-120b-sft-bf16-00006-of-00006.ggufGGUFBF1614.84 GBDownload

Model Details

Model IDmrutkows/granite-5.0-120b-sft-GGUF
Authormrutkows
Pipeline
Licenseapache-2.0
Base modelibm-research/granite-5.0-120b-sft
Last modified2026-08-27T10:42:34.000Z

Model README

---

license: apache-2.0

library_name: llama.cpp

tags:

  • language
  • granite-5.0
  • gguf

base_model:

  • ibm-research/granite-5.0-120b-sft

---

granite-5.0-120b-sft (GGUF)

> [!NOTE]

> This repository contains models that have been converted to the GGUF format with various quantizations from an IBM Granite base model.

>

> Please reference the base model's full model card here:

> https://huggingface.co/ibm-research/granite-5.0-120b-sft

<!-- #### Requirements

  • llama.cpp build: $b9768$ -->

Run mrutkows/granite-5.0-120b-sft-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