Search

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

Local inference engine for Qwen3.8-Flash-Next on NVIDIA Blackwell

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.

Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost.

Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own

Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.

Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~41 in fast mode, 512K context. Plus GLM-5.3-Flash, Qwen3.8 and LFM3-Omni. MoE experts tiered across VRAM, pinned RAM and NVMe, with Xolotl Direct NVMe->VRAM. OpenAI + Anthropic API.

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).

Qwen3.8-Flash-Next is the foundation model developed by Qwen Team, Alibaba Group.

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.io/aeon-7/aeon-vllm-ultimate:latest container, tuned for long-context draft acceptance on DGX Spark. 6 HF variants (BF16/NVFP4/MTP/MTP-XS), docker-compose, and QuickStart.

Optimized SGLang runtime for Qwen3.8-27B FP8 with DFlash2 and Qwen3.8 Flash-Next NVFP4 with FR-Spec on one NVIDIA RTX PRO 6000 Blackwell 96 GB GPU (SM120): 524K context, HiCache and NIXL.

Pure-Rust inference engine for Qwen GGUF models (Qwen3 to Qwen3.8, dense and MoE up to 770B+). CUDA and Vulkan (NVIDIA, AMD), hybrid CPU+GPU experts, MTP speculative decoding, OpenAI and Anthropic compatible server. Up to ~1.7x llama.cpp decode on a 12 GB RTX 3060.

Qwen3.8 27B on SGLang for DGX Spark

Pinned Intel Arc Pro B60/B70 inference recipes, engine patches and measurement records: Qwen3.8-27B EXL3 on one card (262,144 context, 63 tok/s; MTP3 measured lossy on 27% of a fixed 329-item set), Nemotron Bolt 74B, Flash-Next, dual-card routes, and a machine-checked catalog where each speculative row states whether the drafter changes the answer.

Tutel MoE: Optimized Mixture-of-Experts Library, Support GptOss/DeepSeek/Kimi-K2/Qwen3 using FP8/NVFP4/MXFP4

非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。

Local dictation and meeting notes with Whisper or the OpenAI API. Custom Whisper models, MCP history access, and shared engines over LAN/Tailscale. Optional Parakeet/Nemotron (Windows x64, Linux x86_64), Qwen3-ASR/Moonshine (Windows x64), and Parakeet CPU/experimental MLX (Apple Silicon).

~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.

ComfyUI-QwenVL custom node: Integrates the Qwen-VL series, including Qwen2.5-VL, Qwen3-VL, Qwen3.5-VL, Qwen3.6-VL (MoE), and Qwen3.8-VL, with GGUF support for advanced multimodal AI in text generation, image understanding, and video analysis.

Audiobook creation app supporting too many TTS models (Qwen3-TTS, OmniVoice, VibeVoice, etc), focused on high-quality output. Plus audio-synced reader web app and standalone server component.

Open Source Continuous Inference Benchmarking Qwen3.5, DeepSeek, GPTOSS - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 vs H100 & soon™ TPUv6e/v7/Trainium2/3

A ComfyUI custom node integration for local multi-engine multi-language Text-to-Speech and Voice Conversion. Supports: RVC, Echo-TTS, Qwen3-TTS, Cozy Voice 3, Step Audio EditX, IndexTTS-2, Chatterbox (classic and multilingual), F5-TTS, Higgs Audio 2, 3, and VibeVoice with unlimited text length, SRT timing, Character support, and many audio tools

Qwen3.8 is the large language model series developed by Qwen team, Alibaba Group.

基于 FastAPI + Gradio + Qwen3-VL 的多平台视频解析、下载与 AI 内容提取系统。 支持抖音、哔哩哔哩、小红书、快手、好看视频等平台的无水印视频解析与下载，提供在线播放功能。集成 Qwen3-VL 视觉语言模型，可智能提取视频内容并生成文字描述。

A Gradio-based web UI for voice cloning and voice design, powered by Qwen3-TTS & VibeVoice. Can use Whisper or VibeVoice-ASR for automatic transcription.

最极速的Qwen3-TTS推理方案。将 Qwen3-TTS 的 LLM 部分导出为 GGUF，用 llama.cpp 进行加速推理。后者支持 Vulkan 和 Cuda 加速。

DayBee: A cross-platform long-running microphone recorder with real-time transcription. It uses Qwen3-ASR by default. VAD keeps only speech segments and transcribes speech-only chunks.

AI-powered multi-voice audiobook generator — LLM script annotation, voice cloning, voice design, LoRA training, per-line style control, and export to MP3, chaptered M4B, or Audacity multi-track. Built on Qwen3-TTS.