전체 검색
AI 모델 2119
- GLM-5.3-NVFP4↗
Inferact
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. GLM-5.3 supports deployment with the following frameworks. Feel free to try them out:
- Qwen2.5-3B-CyberSecurity-Instruct↗
Mohamedabul
A fine-tuned version of `Qwen2.5-3B-Instruct` specifically designed for advanced cybersecurity analysis. This model is built to bridge the gap between high-level vulnerability descriptions and low-level exploit code execution. 1. **Vulnerability Triage**: Automatically generating structured severity, attack vector, and mitigation reports for any CVE. 2. **Exploit Reverse-Engineering**: Analyzing raw exploit code (C, Python, Bash) to provide an immediate technical breakdown of *how* the exploit works and what vulnerabilities it targets. 3. **Attack Chain Reasoning**: Combining a CVE with raw exploit code to generate a step-by-step kill-chain analysis, from initial access to system compromise. To achieve maximum accuracy, the model was fine-tuned on an expansive historical corpus of modern vulnerabilities and exploits, completely uncapped and unfiltered: - **NVD CVE Database**: Vulnerabilities published between 2020 through 2025. - **Exploit-DB**: Over 45,000+ real-world exploits directly from Offensive Security. - **MITRE CWE**: Full weakness classifications, likelihood of exploit, and abstractions. - **Total Dataset Size**: ~187,700 structured instruction samples.
- ByteCraft↗
SamsungSAILMontreal
- Anima-2.9B↗
Gazingstars123
**Every bit of support helps expand the model's scope and capability even further!** You may still need to install ComfyUI-Anima-2.9B to the custom node folder if your comfyui are not up-to-date (version 0.33.1). Plug and play, there is no custom node needed. Sometimes may not work with other custom nodes Anima-2.9B is a fine-tune and layer-expansion of circlestone-labs/Anima. The base Anima model targets anime, illustration, and non-photorealistic art; this release continues training on that foundation with the expanded architecture. The model is trained on an additional 1.7M anime/illustration samples, with knowledge cutoff in July 2026, making Anima-2.9B one of the most up-to-date anime/illustration model at release.
- Z-Image-Turbo-FP8↗
unsloth
This is an FP8 / INT8 quantized version of Z-Image-Turbo. - Optimized for efficient inference with reduced memory footprint. Same-seed LPIPS vs the bf16 model (lower is better): 0.181 INT8, 0.130 FP8. ⚡️- Image An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer Z-Image is a powerful and highly efficient image generation model family with **6B** parameters. Currently there are four variants:
- Sulphur-2-base↗
SulphurAI
An uncensored video generation model based on LTX 2.3 supporting both t2v and i2v natively, as well as all of the other ltx 2.3 formats. Support the next version of the project, even just a few dollars would go a long way: **Kofi** **Get Started:** To get started with the model, I recommend downloading either of the dev versions, (fp8mixed or bf16) and downloading the distill lora provided. By the way, I'm aware the workflows contain sulphur_final right now, just use the lora or use the full models, don't use both at the same time.
- Ternary-Bonsai-2-27B-Abliterated-v2-PQ2_0-MTP-GGUF↗
BoldingBuilds
**v2 is built to be run with thinking on.** Abliterated Bonsai 2 builds, my own v1 included, tend to write the whole answer inside their reasoning and run out of budget before handing it over. v2 changes one row of the output layer so the model closes its reasoning once the answer is ready. With `reasoning_effort` set to medium it answered every prompt on the main test; at default settings it halves v1's blank answers. **Where v2 stands out: hard requests, given room to think.** StrongReject (150 detailed harmful requests), thinking on, default settings, 16,384-token budget, same judge for every row: Much of that gap is answers the other builds never deliver: they write the answer inside their reasoning and run out of room before closing it.
- t5-base↗
google-t5
1. Model Details 2. Uses 3. Bias, Risks, and Limitations 4. Training Details 5. Evaluation 6. Environmental Impact 7. Citation 8. Model Card Authors 9. How To Get Started With the Model The developers of the Text-To-Text Transfer Transformer (T5) write: > With T5, we propose reframing all NLP tasks into a unified text-to-text-format where the input and output are always text strings, in contrast to BERT-style models that can only output either a class label or a span of the input. Our text-to-text framework allows us to use the same model, loss function, and hyperparameters on any NLP task.
- LFM2.5-24B-A2B-GGUF↗
LiquidAI
LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency. Find more details in the original model card: https://huggingface.co/LiquidAI/LFM2.5-24B-A2B The sampling parameters are the ones recommended for the base model (its `generation_config.json`); each GGUF also carries them as `general.sampling.*` metadata, so llama.cpp applies them by default.
- MiniMax-H3-TextEncoder-Qwen3VL-32B-abliterated-GGUF↗
pottokao
> 🆕 **Newer, better-quality build:** pottokao/MiniMax-H3-TextEncoder-16GB-GGUF — official encoder weights, quantized per tensor by how much each one affects the H3 DiT, K-quants only. At the same 12.65 GB `_vis` size its conditioning error is about half of this Q3_K_S (7.9% vs 14.4%), with 13.7 / 14.8 GB options at 6.4% / 4.9%. > ⚠️ The `_vis` file here stores the visual tower's 5-D `patch_embed` weight as-is; recent `gguf` versions refuse tensors with more than 4 dimensions, so it may fail to load on an up-to-date ComfyUI-GGUF. The new repo stores it the ComfyUI-GGUF way. > 🆕 有新版：pottokao/MiniMax-H3-TextEncoder-16GB-GGUF（官方權重、依 H3 DiT 敏感度逐張量量化、只用 K 系列）。同樣 12.65 GB 誤差約為這顆的一半。這裡的 `_vis` 檔在新版 gguf 套件上可能載不進去。 > 📌 Heads-up: I've been focused on still-image work lately, so I don't have the bandwidth to help with video setups like MiniMax-H3 for now. The files stay up as they are — thanks for understanding! > 最近重心放在平面攝影，影片類（像 MiniMax-H3）暫時比較沒辦法協助排錯。檔案會照舊留著，謝謝體諒！ GGUF (llama.cpp) builds of the **MiniMax-H3 text encoder** — abliterated Qwen3-VL-32B, 50 layers, **Q3_K_S** (≈3.53 BPW).