ibm-granite/granite-4.2-30b
1h
Age
73
Likes
1.8K
Downloads
- Collected
What it costs to run this
29.3B params · 32,768 Context
| Precision | Needs | Cheapest that fits |
|---|---|---|
| 16-bit | 72GB | A100 PCIe$0.27/h |
| 8-bit | 36GB | Q RTX 8000$0.25/h |
| 4-bit | 18GB | Tesla P40$0.07/h |
Weights plus attention cache, with 15% added for activations and allocator overhead. Everything here is arithmetic — we do not measure speed, so we do not rank chips by it. See all GPU prices
New text-generation model. Tags: granite, text-generation, granite-4.2, reasoning, thinking, tool-calling, ibm, conversational
overfeed.news indexes and links. We publish a short excerpt — the full article stays at Hugging Face New Models.
More from Hugging Face New Models
Log in to follow this sourcetencent/WeMM-Embedding-9B
New feature-extraction model. Tags: qwen3_5, image-text-to-text, sentence-transformers, multimodal-embedding, text-embedding, image-embedding, video-embedding, mrl
apodex/Apodex-1.1-mini
New text-generation model. Tags: qwen3_5_moe, image-text-to-text, agent, apodex, arxiv:2608.23283, text-generation, conversational, en
alibaba-pai/MiniMax-H3-Acc-LoRAs
New text-to-video model. Tags: videox_fun, text-to-video, arxiv:2607.26004, base_model:MiniMaxAI/MiniMax-H3, base_model:finetune:MiniMaxAI/MiniMax-H3, license:apache-2.0
BreezeBlue/Breeze-TTS-2
New text-to-speech model. Tags: breeze, text-generation, text-to-speech, speech-generation, voice-clone, voice-design, voice-direction, pytorch