IBM Granite

Enterprise

company

IBM-Granite

Activity Feed

AI & ML interests

LLMs for language and code + Time series and geospatial foundation models

Recent Activity

frreiss new activity 4 days ago

ibm-granite/granite-lib-rag-r1.0:gptoss

gabegoodhart new activity 6 days ago

ibm-granite/granite-4.0-h-small:What happened to medium?

Adirazgold authored a paper 6 days ago

Col-Bandit: Zero-Shot Query-Time Pruning for Late-Interaction Retrieval

View all activity

Papers

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

View all Papers

Articles

Granite 4.0 Nano: Just how small can you go?

Oct 28, 2025

•

123

danielhanchen

posted an update about 3 hours ago

Post

You can now run Qwen3.5 locally! 💜
Qwen3.5-397B-A17B is an open MoE vision reasoning LLM for agentic coding & chat. It performs on par with Gemini 3 Pro, Claude Opus 4.5 & GPT-5.2.

GGUF: unsloth/Qwen3.5-397B-A17B-GGUF
Run Dynamic 3-bit on a 192GB Mac for 20 tokens/s.

Guide: https://unsloth.ai/docs/models/qwen3.5

1 reply

danielhanchen

posted an update 1 day ago

Post

4650

You can now run MiniMax-2.5 locally! 🚀
At 230B parameters, MiniMax-2.5 is the strongest LLM under 700B params, delivering SOTA agentic coding & chat.

Run Dynamic 3/4-bit on a 128GB Mac for 20 tokens/s.
Guide: https://unsloth.ai/docs/models/minimax-2.5
GGUF: unsloth/MiniMax-M2.5-GGUF

1 reply

frreiss

in ibm-granite/granite-lib-rag-r1.0 4 days ago

gptoss

#10 opened 4 days ago by

frreiss

gabegoodhart

in ibm-granite/granite-4.0-h-small 6 days ago

What happened to medium?

#11 opened 8 days ago by

SuperbEmphasis

danielhanchen

posted an update 6 days ago

Post

5044

We collaborated with Hugging Face to enable you to train MoE models 12× faster with 35% less VRAM via our new Triton kernels (no accuracy loss). 🤗

Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe

1 reply

Adirazgold

authored a paper 6 days ago

Col-Bandit: Zero-Shot Query-Time Pruning for Late-Interaction Retrieval

Paper • 2602.02827 • Published 14 days ago • 2

gabegoodhart

in ibm-granite/granite-docling-258M-GGUF 7 days ago

Dissapointing quality with scanned documents

#1 opened 10 days ago by

Awschult

pengyuan

updated a model 7 days ago

ibm-granite/granite-vision-3.3-2b-chart2csv-preview

Image-Text-to-Text • 3B • Updated 7 days ago • 2.12k • 11

gabegoodhart

in ibm-granite/granite-embedding-reranker-english-r2 10 days ago

no gguf support

#4 opened 3 months ago by

kalle07

gabegoodhart

in ibm-granite/granite-embedding-english-r2 10 days ago

GGUF variant/ollama support

#2 opened 5 months ago by

ruddbanga7

danielhanchen

posted an update 11 days ago

Post

3624

We created a tool-calling guide for local LLMs!

Learn how to use any open model like Qwen3-Coder-Next and GLM-4.7-Flash for function calling.

Guide: https://unsloth.ai/docs/basics/tool-calling-guide-for-local-llms

We provide hands-on examples for: story writing, Python execution, terminal tool calls, maths and more.

7 replies

danielhanchen

posted an update 13 days ago

Post

3718

Qwen releases Qwen3-Coder-Next! 💜 Run the locally on 46GB RAM or less.

Thhe model excels at agentic coding & local use. With 256K context, it delivers similar performance to models with 10-20× more active parameters.

GGUF: unsloth/Qwen3-Coder-Next-GGUF
Guide: https://unsloth.ai/docs/models/qwen3-coder-next