IBM Granite

company

AI & ML interests

Enterprise-grade AI models

Recent Activity

Avihu updated a model about 20 hours ago

ibm-granite/granite-vision-4.1-4b

eustlb new activity 1 day ago

ibm-granite/granite-speech-4.1-2b-nar:Add native transformers GraniteSpeechNarForCTC format

artemspector updated a model 2 days ago

ibm-granite/granite-vision-4.1-4b

View all activity

Papers

ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding

SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

View all Papers

Articles

Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality

Granite 4.1 LLMs: How They’re Built

Granite 4.0 3B Vision: Compact Multimodal Intelligence for Enterprise Documents

What's New in Mellea 0.4.0 + Granite Libraries Release

Granite 4.0 1B Speech: Compact, Multilingual, and Built for the Edge

Granite 4.0 Nano: Just how small can you go?

View all articles

updated a model about 20 hours ago

ibm-granite/granite-vision-4.1-4b

Image-Text-to-Text • 4B • Updated about 20 hours ago • 189k • 95

in ibm-granite/granite-speech-4.1-2b-nar 1 day ago

Add native transformers GraniteSpeechNarForCTC format

#6 opened 1 day ago by

updated a model 2 days ago

ibm-granite/granite-vision-4.1-4b

Image-Text-to-Text • 4B • Updated about 20 hours ago • 189k • 95

posted an update 4 days ago

Post

3842

We’re releasing new Qwen3.6 quants that run 2.5× faster on your GPU. ⚡

Qwen3.6-27B NVFP4 runs on 24GB VRAM.
35B-A3B can hit 17,561 tok/s (B200).

We also improved accuracy, tool calling, agent use, and looping.

Qwen3.6 NVFP4: https://huggingface.co/collections/unsloth/nvfp4
Guide: https://unsloth.ai/docs/models/qwen3.6#nvfp4

1 reply

·

updated a model 5 days ago

ibm-granite/granite-swash-3b-a600m

Text Generation • 3B • Updated 5 days ago • 655 • 8

published a model 6 days ago

ibm-granite/granite-timeseries-ttm-r3

Time Series Forecasting • 1.41M • Updated 12 days ago • 3.56k • 4

published 2 models 7 days ago

ibm-granite/granite-swash-2b

Text Generation • 2B • Updated 7 days ago • 250 • 4

ibm-granite/granite-swash-3b-a600m

Text Generation • 3B • Updated 5 days ago • 655 • 8

updated a model 7 days ago

ibm-granite/granite-3.1-1b-a400m-instruct

Text Generation • 1B • Updated 7 days ago • 5.36k • 19

posted an update 7 days ago

Post

5840

DeepSeek-V4 can now run locally with Unsloth GGUFs! 🐳

Run lossless DeepSeek-V4-Flash on 168GB RAM or
3-bit works on 110GB Mac, RAM, VRAM setups.

Run via Unsloth Studio or llama.cpp.

GGUF: unsloth/DeepSeek-V4-Flash-GGUF
Guide: https://unsloth.ai/docs/models/deepseek-v4

updated a model 7 days ago

ibm-granite/granite-swash-2b

Text Generation • 2B • Updated 7 days ago • 250 • 4

updated a model 12 days ago

ibm-granite/granite-timeseries-ttm-r3

Time Series Forecasting • 1.41M • Updated 12 days ago • 3.56k • 4

updated a collection 13 days ago

Granite Experiments

Experimental projects under consideration for the Granite family. • 13 items • Updated 6 days ago • 20

updated 2 models 13 days ago

ibm-granite/granite-swash-3b-a600m

Text Generation • 3B • Updated 5 days ago • 655 • 8

ibm-granite/granite-swash-2b

Text Generation • 2B • Updated 7 days ago • 250 • 4

updated a model 14 days ago

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

2B • Updated 14 days ago • 552

updated a collection 14 days ago

Granite Quantized Models

Quantized versions of IBM Granite models. • 50 items • Updated 14 days ago • 36

updated a collection 14 days ago

Granite Quantized Models

Quantized versions of IBM Granite models. • 50 items • Updated 14 days ago • 36

updated a model 14 days ago

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

2B • Updated 14 days ago • 552