全站搜索
AI 模型 85012
- multiberts-seed_14↗
Google
- paligemma-3b-ft-okvqa-224↗
Google
- t5-efficient-mini-nl24↗
Google
- Llama-3-8B-Instruct-262k↗
gradientai
- Pantheon-Reasoning-26B-A4B-1.1-V2↗
Gryphe
- Qwen3.8-Flash-Next-cmf↗
infosave
Qwen3.8-Flash-Next — a 125B hybrid mixture-of-experts model, 6B active per token (36 Gated DeltaNet + 12 sparse-attention layers, 512 experts per layer, 51B n-gram table, 262k context, thinking mode) — as CMF files, text only. It runs with `cortiq`, a Rust engine with no Python. Experts stream from the memory-mapped file as tokens need them, so the default 77 GB file runs on one GPU (measured from a 12 GB VRAM budget up to a whole 32 GB card) with the rest in system RAM. **RTX 3090 (24 GB), cortiq 0.8.15: 49.1 tok/s decode; first token after a 1,000-token prompt in 9.9 s.** RTX 5090 (cortiq 0.8.8): 81.7 tok/s, 108.6 with speculative decoding. Use cortiq 0.8.15 or later (prebuilt binaries). Without `--no-think` the model reasons first; raise `--max-tokens` (default 256). Each `cortiq run` loads the model again (10–30 s to the first token); for chat, keep it loaded with `cortiq serve`.
- Z-Image-GGUF↗
jayn7
- Mellum2-12B-A2.5B-Thinking-GGUF-MXFP4_MOE↗
JetBrains
- nexus-science-GGUF↗
King3Djbl
- kling-video-v2-1-master↗
快手 · 可灵
