Phocinae/Phocinae-Largha-150M-v1
6h
108
89
- Collected
What it costs to run this
0.14
| Precision | Needs | Cheapest that fits |
|---|---|---|
| 16-bit | 1.5 | Quadro P2000 |
| 8-bit | 0.7 | Quadro P2000 |
| 4-bit | 0.4 | Quadro P2000 |
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-classification model. Tags: modernbert, fill-mask, decision-making, typed-decisions, text-classification, small-model, bilingual, calibration
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
nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2
New image-text-to-text model. Tags: gguf, qwen3.8, efficient-thinking, reasoning, coding, uncensored, sft, simpo
Qwen/Qwen-Image-2.1-Turbo
New text-to-image model. Tags: diffusers, qwen, image-generation, image-editing, text-to-image, base_model:Qwen/Qwen-Image-2.1, base_model:finetune:Qwen/Qwen-Image-2.1, license:other
ausboss/Qwen-Image-2.1-Outfit-Swap-Consistency-LoRA
New image-to-image model. Tags: lora, image-editing, outfit-swap, consistency, virtual-try-on, qwen-image, qwen-image-2.1, comfyui
ConwayResearch/Underdog-Saluki-27B-1.0
New text-generation model. Tags: gguf, llama.cpp, 2-bit, tool-calling, function-calling, agents, qwen3.8, text-generation