전체 검색
AI 모델 84760
- UltraBERT-150M-nli↗
tasksource
- Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF↗
TeichAI
This model was trained on a **Claude Opus 4.5 (reasoning)** dataset with a high reasoning effort. - 🤖 Related Models: | Model | Effective parameters | Active parameters | | ------------- | ------------- | ------------- | | `Nemotron-Orchestrator-8B-Claude-4.5-Opus-Distill-GGUF` | 8 B | 8 B | | `Qwen3-8B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF` | 8 B | 8 B | | `Qwen3-4B-Thinking-2507-Claude-4.5-Opus-High-Reasoning-Distill-GGUF` | 4 B | 4 B | - ∑ Stats (Dataset) - Costs: $ 52.3 (USD) - Total tokens (input + output): 2.13 M
- Llama-3.1-8B-Instruct-GGUF↗
tensorblock
- Zarablend-MX-L2-7B-GGUF↗
TheBloke
- Survivor-v1-2B-GGUF↗
theprint
- NVIDIA-Nemotron-3.5-Lightning-30B-A3B-W4A16↗
useful-quants
This is a calibrated W4A16 quantization of NVIDIA Nemotron 3.5 Lightning 30B-A3B, intended for high-throughput NVIDIA GPU serving with vLLM. It has been validated on a single 24 GB RTX 3090 at a 640K production context window. - **Model developer:** NVIDIA - **Quantization / packaging:** useful-quants - **Source checkpoint:** NVIDIA's BF16 release at revision `63a200063804e06fdb41d6717e43bc92f67859d2` - **Governing license:** OpenMDW 1.1; the unmodified upstream license is included as `LICENSE`. This is a third-party, post-training quantization. useful-quants did not train, fine-tune, align, or otherwise develop Nemotron. The conversion does not change NVIDIA's intended-use, safety, or license terms; see the upstream model card for those terms, language coverage, architecture, reasoning behavior, training/data disclosure, and NVIDIA's source-model benchmark suite.
- VibeVoice-7B-hf↗
vibevoice
- Kroma-GGUF↗
voldemir
- Wan2.2-T2V-A14B-Diffusers↗
Wan-AI
💜 Wan    |    🖥️ GitHub    |   🤗 Hugging Face    |   🤖 ModelScope    |    📑 Technical Report    |    📑 Blog    |   💬 WeChat Group    |    📖 Discord    We are excited to introduce **Wan2.2**, a major upgrade to our foundational video models. With **Wan2.2**, we have focused on incorporating the following innovations: - 👍 **Effective MoE Architecture**: Wan2.2 introduces a Mixture-of-Experts (MoE) architecture into video diffusion models. By separating the denoising process cross timesteps with specialized powerful expert models, this enlarges the overall model capacity while maintaining the same computational cost.
- FreeSolo-B-341M↗
zekun-shi
