전체 검색
AI 모델 84768
- mathstral-7B-v0.1-GGUF↗
second-state
- paraphrase-albert-base-v2↗
sentence-transformers
- flux-3-klein-image-photo-aesthetics-distilled-assisted-512-v2-kohaku-fa↗
SimpleTuner
- wikiser-bert-base↗
taidng
- WAN2.2LORASforVVideo↗
thatboymentor
- Falcon-Perception↗
tiiuae
- resnet50.am_in1k↗
timm
- Qwen3-VL-Embedding-8B↗
tomaarsen
- Qwen3.5-122B-A10B-GGUF↗
unsloth
Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants. Disable thinking via `--chat-template-kwargs '{"enable_thinking":false}'`. Read our guide. - All GGUFs now use our new imatrix data. See some improvements in chat, coding, long context, and tool-calling use-cases. - GGUFs updated with an improved quantization algorithm. - Updated with fixed chat template for improved tool-calling & coding performance! - See our new benchmarks for 122B-A10B here.
- Qwen3.6-27B-NVFP4↗
unsloth
* **2.5x faster** throughput than other NVFP4 quants. * This is an Unsloth NVFP4 quantized checkpoint calibrated on a mixture of our Unsloth dataset + UltraChat dataset. * Works on a 24GB VRAM GPU. Benchmarks on 1xB200 128 concurrency. For accuracy benchmarks, we conducted MMLU-Pro, AIME 2025, GPQA for FP8, BF16, NVIDIA's NVFP4 and our NVFP4s - we show our faster quants do similarly on all: Read all benchmarks in our NVFP4 blog
