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

ibm-granite/granite-speech-4.1-2b-plus-GGUF overview

Granite Speech 4.1 2B Plus GGUF NOTE This repository contains models that have been converted to the GGUF format with various quantizations from an IBM Granite…

llama.cppgguflanguagegranite-4.1speechbase_model:ibm-granite/granite-speech-4.1-2b-plusbase_model:quantized:ibm-granite/granite-speech-4.1-2b-pluslicense:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~976.2 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline

Repository Files & Downloads

6 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
granite-speech-4.1-2b-plus-Q4_K_M.ggufGGUFQ4_K_M976.2 MBDownload
granite-speech-4.1-2b-plus-Q5_K_M.ggufGGUFQ5_K_M1.10 GBDownload
granite-speech-4.1-2b-plus-Q6_K.ggufGGUFQ6_K1.25 GBDownload
granite-speech-4.1-2b-plus-Q8_0.ggufGGUFQ8_01.62 GBDownload
granite-speech-4.1-2b-plus-bf16.ggufGGUFBF163.04 GBDownload
mmproj-model-f16.ggufGGUFF161.09 GBDownload

Model Details

Model IDibm-granite/granite-speech-4.1-2b-plus-GGUF
Authoribm-granite
Pipeline
Licenseapache-2.0
Base modelibm-granite/granite-speech-4.1-2b-plus
Last modified2026-06-30T22:40:17.000Z

Model README

---

license: apache-2.0

library_name: llama.cpp

tags:

  • language
  • granite-4.1
  • speech
  • gguf

base_model:

  • ibm-granite/granite-speech-4.1-2b-plus

---

Granite-Speech-4.1-2B-Plus (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-granite/granite-speech-4.1-2b-plus

Requirements

  • llama.cpp build: b9768

Run ibm-granite/granite-speech-4.1-2b-plus-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