ニュースとサイト内検索
ニュース、ツール、モデル、ガイド、特集、ワークフロー、プロンプトを関連付けて検索。
AI モデル 56
“AI Code Guide”
NV-Reason-CT
NV-Reason-CT is a 3D vision-language model (VLM) for CT image analysis. It combines a native 3D vision encoder (3D ViT) with a language model and is designed for radiology report generation, general question answering, and multi-step reasoning across chest and abdominal CT volumes. Computed tomography encodes clinically important anatomy across hundreds of slices, yet most vision–language systems either operate on 2D images or compress volumetric features before language decoding. The 3D vision encoder converts a 384×384×384-mm input volume into a 24×24×24 grid of 13,824 visual tokens. All tokens and their corresponding 3D positions are passed to the language model without spatial downsampling, while 3D MRoPE preserves their spatial relationships within the LLM. Input volumes are automatically cropped to the chest or abdomen and resampled to 2-mm isotropic resolution before processing. The model was trained end-to-end using Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO) on a curated dataset of approximately 550,000 structured QA examples from 70,111 unique CT volume inputs. The training corpus integrates standardized reports, abnormality-focused QA, multi-turn interactions, and radiologist-authored reasoning collected through recorded and transcribed expert CT interpretations. These expert annotations also guide the generation of report-grounded synthetic reasoning data for SFT, while GRPO uses verifiable rewards over chest and abdominal abnormality sets.
GLM-5.3-GGUF
You can now run GLM-5.3 in Unsloth Desktop with toggles for Low, High and Max thinking. Read our GLM-5.3 guide for analysis and instructions. GLM-5.3 uses the same base model as GLM-5.2 — every gain comes from post-training. Compared with GLM-5.2, it is much better at complex coding and long-horizon tasks: + Stronger Coding: GLM-5.3 is the most capable open-weights model for coding, with a 50% improvement over GLM-5.2 on our in-house Z.ai Code Bench. It also achieve open-source SOTA on public benchmarks including Terminal Bench 3.0 and Agents' Last Exam. + Emergent Cyber Capability: As we scaled post-training, cyber capability developed faster than we expected. GLM-5.3 is state of the art on CyberGym for vulnerability discovery, and its gains are largest further up the exploitation chain, where it more than doubles GLM-5.2 on exploitation benchmarks.
Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF
🔥 **Update (April 5):** I’ve released the complete training notebook, codebase, and a comprehensive PDF guide to help beginners and enthusiasts understand and reproduce this model's fine-tuning process. > ❤️ Special thanks to the **Unsloth** open-source library and @KyleHessling1 for their support. 👉 **GitHub Repository: Jackrong-llm-finetuning-guide** Visit the repo to dive into the codebase and reproduce the results locally or on Colab.
Qwen3-Coder-Next-GGUF
Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants. - **Feb 19 update**: Tool-calling should now be even better after llama.cpp fixes parsing. - **Quantization benchmarks**: See third-party Aider, LiveCodeBench v6, MMLU Pro, GPQA benchmarks for GGUFs here. - **Feb 4 update**: llama.cpp fixed a bug that caused Qwen to loop and have poor outputs. We updated GGUFs - please re-download and update llama.cpp for improved outputs. - It is recommended to have >45GB unified memory or RAM/VRAM to run 4-bit quants. - For best results, use any 2-bit XL quant or above (requires >30GB unified memory /combined RAM + VRAM). - See how to run the model via Claude Code & OpenAI Codex. - For complete detailed instructions (sampling parameters etc.), see our guide: docs.unsloth.ai/models/qwen3-coder-next
Qwen3.6-35B-A3B-UD-MLX-4bit
NEW: Developer Role Support so Qwen3.6 can work in Codex, OpenCode and more! Qwen3.6 can now be run and fine-tuned in Unsloth Studio . Read our guide . Tool calling improvements: Makes parsing nested objects to make tool calling succeed more. Example of Qwen3.6 (4-bit GGUF) running in Unsloth Studio with tool-calling: > [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc. Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience.
LTX-2-GGUF
This is a GGUF quantized version of LTX-2. unsloth/LTX-2-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance. - Important layers are upcasted to higher precision. - To use the model, read our guides for ComfyUI or stable-diffusion.cpp. - Uses tooling from ComfyUI-GGUF by city96. This model card focuses on the LTX-2 model, as presented in the paper LTX-2: Efficient Joint Audio-Visual Foundation Model. The codebase is available here. LTX-2 is a DiT-based audio-video foundation model designed to generate synchronized video and audio within a single model. It brings together the core building blocks of modern video generation, with open weights and a focus on practical, local execution.
Muse-Glimmer-30B
See our Muse Glimmer guide for quantization analysis and instructions. You can now run Muse Glimmer in Unsloth with toggles for thinking. Muse Glimmer is a 30-billion-parameter causal language model with a dedicated perception encoder, distilled from Muse Spark and purpose-built for autonomous agentic tasks on consumer hardware. The model integrates multi-step reasoning, reliable tool use, multimodal understanding, and failure recovery into a single model that runs locally without requiring cloud infrastructure or network access. Building effective agents requires key capabilities working together to achieve the user’s goals. Muse Glimmer is trained and evaluated on these capabilities:
Llama-3.1-Tulu-3-8B
Tülu 3 is a leading instruction following model family, offering a post-training package with fully open-source data, code, and recipes designed to serve as a comprehensive guide for modern techniques. This is one step of a bigger process to training fully open-source models, like our OLMo models. Tülu 3 is designed for state-of-the-art performance on a diversity of tasks in addition to chat, such as MATH, GSM8K, and IFEval. The Tülu3 models have limited safety training, but are not deployed automatically with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). It is also unknown what the size and composition of the corpus was used to train the base Llama 3.1 models, however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this. PPO settings for RLVR: - **Learning Rate**: 3 × 10⁻⁷ - **Discount Factor (gamma)**: 1.0 - **General Advantage Estimation (lambda)**: 0.95 - **Mini-batches (N_mb)**: 1 - **PPO Update Iterations (K)**: 4 - **PPO's Clipping Coefficient (epsilon)**: 0.2 - **Value Function Coefficient (c1)**: 0.1 - **Gradient Norm Threshold**: 1.0 - **Learning Rate Schedule**: Linear - **Generation Temperature**: 1.0 - **Batch Size (effective)**: 224 - **Max Token Length**: 2,048 - **Max Prompt Token Length**: 2,048 - **Penalty Reward Value for Responses without an EOS Token**: -10.0 - **Response Length**: 2,048 - **Total Episodes**: 100,000 - **KL penalty coefficient (beta)**: 0.05 - **Warm up ratio (omega)**: 0.0
audiogen-medium
AudioGen is an autoregressive transformer LM that synthesizes general audio conditioned on text (Text-to-Audio). Internally, AudioGen operates over discrete representations learnt from the raw waveform, using an EnCodec tokenizer. AudioGen was presented at AudioGen: Textually Guided Audio Generation by *Felix Kreuk, Gabriel Synnaeve, Adam Polyak, Uriel Singer, Alexandre Défossez, Jade Copet, Devi Parikh, Yaniv Taigman, Yossi Adi*. AudioGen 1.5B is a variant of the original AudioGen model that follows MusicGen architecture. More specifically, it is trained over a 16kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz with a delay pattern between the codebooks. Having only 50 auto-regressive steps per second of audio, this AudioGen model allows faster generation while reaching similar performances to the original AudioGen model introduced in the paper.
Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled
🔥 **Update (April 5):** I’ve released the complete training notebook, codebase, and a comprehensive PDF guide to help beginners and enthusiasts understand and reproduce this model's fine-tuning process. 👉 **GitHub Repository: Jackrong-llm-finetuning-guide** Visit the repo to dive into the codebase and reproduce the results locally or on Colab. **🔗 Qwopus3.5-27b Complete Fine-Tuning Guide (PDF)** * **The Full Pipeline:** A step-by-step walkthrough—from downloading the base model and unifying heterogeneous data, to configuring trainer hyperparameters and publishing to Hugging Face. * **Beginner Friendly:** Includes an introductory guide to getting started with Google Colab and Unsloth. * *Feedback welcome! If you spot any areas for improvement, please let me know and I will update it promptly.*