ibm-granite/granite-4.2-30b
2mo
73
1.8K
- Collected
What it costs to run this
29.3
| Precision | Needs | Cheapest that fits |
|---|---|---|
| 16-bit | 72 | A800 PCIE |
| 8-bit | 36 | Q RTX 8000 |
| 4-bit | 18 | L4 |
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 source
LiquidAI/d1-2B
New image-text-to-text model. Tags: lfm3_vl, feature-extraction, liquid, lfm3, edge, decision, classification, extraction
divagr1925/Qwen3.5-4B-Qwenputer
New text-generation model. Tags: qwen3_5_text, text-generation, qwen3.5, risc-v, rv32im, arithmetic, compiled-weights, gated-deltanet
Edge0/Audio8-TTS-Realistic-0.6b
New text-to-speech model. Tags: arktts, feature-extraction, audio, text-to-speech, tts, voice-cloning, zero-shot, multilingual
nvidia/MotionBricks
New robotics model. Tags: pytorch, nvidia, motionbricks, motion-generation, pose-conditioned, robotics, animation, arxiv:2604.24833