サイト内検索
AI モデル 84759
- gemma-4-31B-it-qat-GGUF↗
unsloth
Jun 9 Update: Added MTP support. See our MTP Guide . Gemma 4 can now be run and fine-tuned in Unsloth Studio . Read our guide . See all versions of Gemma 4 QAT (GGUF, 16-bit etc.) in our collection . Example of Gemma 4 E4B (4-bit GGUF) running in Unsloth Studio with tool-calling: This model ships a Multi-Token Prediction drafter at the repo root (`mtp-gemma-4-31B-it.gguf`, a near-lossless smart Q4_0). A recent llama.cpp auto-discovers it from `-hf`, so you do not pass `--model-draft`: The drafter shares the target's KV cache and does not change the output (the target verifies every drafted token). See the `MTP/` folder for the other precisions and explicit usage.
- Qwen-Image-Layered-GGUF↗
unsloth
> [!NOTE] > This is a GGUF quantized version of Qwen-Image-Layered. > unsloth/Qwen-Image-Layered-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance. Important layers are upcasted to higher precision.   🤗 HuggingFace    |   🤖 ModelScope    |    📑 Research Paper    |    📑 Blog    |    🤗 Demo    We are excited to introduce **Qwen-Image-Layered**, a model capable of decomposing an image into multiple RGBA layers. This layered representation unlocks **inherent editability**: each layer can be independently manipulated without affecting other content. Meanwhile, such a layered representation naturally supports **high-fidelity elementary operations**-such as resizing, reposition, and recoloring. By physically isolating semantic or structural components into distinct layers, our approach enables high-fidelity and consistent editing.
- Qwen3.5-4B-Base↗
unsloth
> [!Note] > This repository contains model weights and configuration files for the pre-trained only model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, etc. > > The intended use cases are fine-tuning, in-context learning experiments, and other research or development purposes, not direct interaction. > However, the control tokens, e.g., ` ` and ` ` were trained to allow efficient LoRA-style PEFT with the official chat template, mitigating the need to finetune embeddings, a significant optimization given Qwen3.5's larger vocabulary. Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency.
- dQwen3.5-2B-Base↗
UT-IFML
- I-DLM-8B↗
yifanyu
- opt-tiny-random↗
yujiepan
This model is randomly initialized, using the config from facebook/opt-30b but with smaller size. Note the model is in float16.
- c11↗
zeras141a
- lfm25-8b-a1b-GGUF↗
AlexAtomic
**LFM2.5 8B A1B**, self-quantized to GGUF by Atomic Chat. Built straight from Liquid AI's original weights with a per-tensor importance matrix. Runs fully offline. > [!NOTE] > These GGUFs are **self-quantized from the original weights**, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model. > [!IMPORTANT] > Always pass `--jinja` so the **LFM2.5 8B A1B chat template** is applied. Without it the model can emit malformed turns.
- gemma3_4b_deedexp↗
anandkaman
- TiC-CLIP-basic-cumulative↗
apple