전체 검색
AI 모델 85012
- RadianceChromeVoluptuous_z_image_v1.0↗
AIImageStudio
- FLUX.2-dev-Fun-Controlnet-Union↗
alibaba-pai
- L-MChat-7b↗
Artples
L-MChat-7b is a merge of the following models: * Nexusflow/Starling-LM-7B-beta * FuseAI/FuseChat-7B-VaRM
- sub38-157↗
asim22
- bagel-8b-v1.0-GGUF↗
bartowski
- google_functiongemma-270m-it-GGUF↗
bartowski
- nvidia_Llama-3.1-8B-UltraLong-2M-Instruct-GGUF↗
bartowski
- Kimibrain-Uncensored↗
burabeeh
- sd15↗
ckpt
- Qwen3-Coder-30B-A3B-Instruct-AWQ↗
dark-side-of-the-code
AWQ **W4A16** (4-bit weights, group size 128) quantization of `Qwen/Qwen3-Coder-30B-A3B-Instruct`, produced with llm-compressor for serving on a single 24 GB GPU with vLLM. Qwen3-Coder-30B-A3B is a Mixture-of-Experts model (128 experts, 8 active per token) using standard **GQA** attention — so it serves on consumer Ada GPUs with the stock attention backends, no special kernels required. Notes: - At `--max-model-len 65536` on a 24 GB card the KV pool holds ~118K tokens (~1.8x concurrency). The base model's native context is 262K; 64K is the practical cap at 24 GB. - Tool calling works via vLLM's first-class `qwen3_coder` parser. - Non-thinking model — no reasoning parser needed. - Pass `--override-generation-config` if your client doesn't send sampling params, or vLLM will default to `temperature=1.0`, which is far too hot for coding.
