Diffuspace/Clover-35B-A3B-Preview
22h
107
105
- Collected
What it costs to run this
34.7
| Precision | Needs | Cheapest that fits |
|---|---|---|
| 16-bit | 77 | A100 SXM4 |
| 8-bit | 39 | Q RTX 8000 |
| 4-bit | 19 | 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: clover_moe, text-generation, clover, mixture-of-experts, diffusion, custom-code, conversational, custom_code
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
Pika-Labs/Pika-H3-Flex
New image-to-video model. Tags: diffusers, video-generation, audio-video-generation, lora, image-to-video, base_model:MiniMaxAI/MiniMax-H3, base_model:adapter:MiniMaxAI/MiniMax-H3, license:other
mistralai/Mistral-Large-4-1T-A52B
New image-text-to-text model. Tags: mistral_large4, image-text-to-text, vLLM, SGLang, llama.cpp, conversational, en, fr
Efficient-Large-Model/Open-H3-Regenerate-2K
New video-to-video model. Tags: diffusers, minimax-h3, lora, video-refinement, sol-engine, video-to-video, base_model:MiniMaxAI/MiniMax-H3, base_model:adapter:MiniMaxAI/MiniMax-H3
maya-research/maya2-native
New text-to-speech model. Tags: maya3, text-to-speech, tts, indic, multilingual, voice-cloning, streaming, mimi