전체 검색

AI 모델 84759

• Octans-Qwen3-UI-Code-4B-GGUF↗

  prithivMLmods

• LTX-2.3-GGUF↗

  QuantStack

  This GGUF file is a direct conversion of Lightricks/LTX-2.3 Type | Name | Location | Download | ------------ | -------------------------------------------------- | --------------------------------- | ------------------------- | Main Model | LTX-2.3 | `ComfyUI/models/unet` | GGUF (this repo) | Text Encoder | Gemma 3 | `ComfyUI/models/text_encoders` | Safetensors / GGUF | | Text Encoder | Text Projection | `ComfyUI/models/text_encoders` | Safetensors| | VAE Video / VAE Audio | vae | `ComfyUI/models/vae` | Safetensors | Since this is a quantized model, all original licensing terms and usage restrictions remain in effect.

• Qwen3 30B A3B 2507 (Reasoning)↗

  阿里巴巴 · Qwen

• Qwen3-Next-80B-A3B-Instruct-GGUF↗

  阿里巴巴 · Qwen

  Over the past few months, we have observed increasingly clear trends toward scaling both total parameters and context lengths in the pursuit of more powerful and agentic artificial intelligence (AI). We are excited to share our latest advancements in addressing these demands, centered on improving scaling efficiency through innovative model architecture. We call this next-generation foundation models **Qwen3-Next**. **Qwen3-Next-80B-A3B** is the first installment in the Qwen3-Next series and features the following key enchancements: - **Hybrid Attention**: Replaces standard attention with the combination of **Gated DeltaNet** and **Gated Attention**, enabling efficient context modeling for ultra-long context length. - **High-Sparsity Mixture-of-Experts (MoE)**: Achieves an extreme low activation ratio in MoE layers, drastically reducing FLOPs per token while preserving model capacity. - **Stability Optimizations**: Includes techniques such as **zero-centered and weight-decayed layernorm**, and other stabilizing enhancements for robust pre-training and post-training. - **Multi-Token Prediction (MTP)**: Boosts pretraining model performance and accelerates inference. We are seeing strong performance in terms of both parameter efficiency and inference speed for Qwen3-Next-80B-A3B: - Qwen3-Next-80B-A3B-Base outperforms Qwen3-32B-Base on downstream tasks with 10% of the total training cost and with 10 times inference throughput for context over 32K tokens. - Qwen3-Next-80B-A3B-Instruct performs on par with Qwen3-235B-A22B-Instruct-2507 on certain benchmarks, while demonstrating significant advantages in handling ultra-long-context tasks up to 256K tokens.

• pixal3d-q8_0-v1↗

  raven38

  GGUF weights for `pixal3d.cpp`, a GGML-based C++ image→3D pipeline. This is the **Web release set**: Q8_0 quantization, 9 files, 7.54 GiB, sized so that Texture Flow fits the browser WebGPU per-buffer budget (measured peak 2,517 MB against 4,095 MB, 38 % headroom). The repository layout is flat and the file names are exact, because the consuming client verifies every file's `size_bytes` and SHA-256 against the committed manifest `pixal3d-models.json` before the set is marked usable. or pass `--model-base-url` with `--model-manifest` to the desktop installer. The client streams each file into origin-owned storage and refuses the set unless every file matches the manifest exactly.

• flammenai_-_flammen-mistral-7B-gguf↗

  RichardErkhov

• lemon-mint_-_gemma-ko-7b-instruct-v0.71-gguf↗

  RichardErkhov

• mylesgoose_-_Llama-3.2-1B-Instruct-abliterated3-gguf↗

  RichardErkhov

• sam-paech_-_qwen-2.5-32b-instruct-resized-gguf↗

  RichardErkhov

• MiniMax-H3↗

  Rin247