LiquidAI/LFM2.5-24B-A2B
1d
103
2.6K
- Collected
What it costs to run this
24.0
| Precision | Needs | Cheapest that fits |
|---|---|---|
| 16-bit | 54 | A800 PCIE |
| 8-bit | 27 | Q RTX 8000 |
| 4-bit | 14 | Tesla P100 |
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: lfm2_moe, text-generation, liquid, lfm2.5, edge, moe, conversational, en
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/LFM2.5-24B-A2B-GGUF
New text-generation model. Tags: gguf, liquid, lfm2.5, llama.cpp, text-generation, en, ar, zh
openbmb/MiniCPM-V-4.7-35B-A3B-gguf
New image-text-to-text model. Tags: gguf, minicpm-v, multimodal, On-Device Model, lightweight, image-text-to-text, base_model:openbmb/MiniCPM-V-4.7-35B-A3B, base_model:quantized:openbmb/MiniCPM-V-4.7-35B-A3B
fishaudio/drama-3
New text-to-speech model. Tags: fish_omni, fish-audio, text-to-speech, multi-speaker, audio-editing, emotional-speech-generation, zh, en
autotrust/JEV-35B-NVFP4
New text-classification model. Tags: qwen3_5_moe, image-text-to-text, system-one, typed-decisions, decision-model, calibrated-probabilities, jev, noul