InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. text generation model by HemmingwayAI · transformers

    Stale Hugging Face Hub, HemmingwayAI 56 ♥cc-by-nc-4.0Updated 16 days ago

    HemmingwayAI/Hemmingway-1.5
  2. Thinklite-27B

    Models

    image text to text model by Sparset · transformers

    Stale Hugging Face Hub, Sparset 52 ♥apache-2.0Updated 13 days ago

    Sparset/Thinklite-27B
  3. Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...

    Indexed OpenRouter model list, qwen Updated 3 months ago

    qwen/qwen3.8-2.4t-a95b
  4. image text to text model by sensenova · transformers

    Stale Hugging Face Hub, sensenova 103 ♥apache-2.0Updated 14 days ago

    sensenova/SenseNova-6.8-Code2Video
  5. image text to text model by DavidAU

    Stale Hugging Face Hub, DavidAU 31 ♥apache-2.0Updated 27 days ago

    DavidAU/Qwen3.8-Flash-Next-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO-GGUF
  6. Tess-4.5-27B

    Models

    image text to text model by migtissera · transformers

    Stale Hugging Face Hub, migtissera 56 ♥apache-2.0Updated 30 days ago

    migtissera/Tess-4.5-27B
  7. sabi-noema

    Models

    text generation model by sabicap · transformers

    Stale Hugging Face Hub, sabicap 33 ♥apache-2.0Updated 29 days ago

    sabicap/sabi-noema
  8. Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...

    Indexed OpenRouter model list, qwen Updated 55 days ago

    qwen/qwen3.8-max-prime
  9. image text to text model by DavidAU

    Stale Hugging Face Hub, DavidAU 47 ♥apache-2.0Updated 27 days ago

    DavidAU/Qwen3.8-27B-Jumbo-Fusion-IQ-747-900-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF
  10. Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...

    Indexed OpenRouter model list, qwen Updated 2 months ago

    qwen/qwen3.8-max-0902
  11. Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...

    Indexed OpenRouter model list, qwen Updated 2 months ago

    qwen/qwen3.8-max-0902:batch
  12. text generation model by Kujira · gguf

    Stale Hugging Face Hub, Kujira 57 ♥apache-2.0Updated 39 days ago

    Kujira/Underdog-Saluki-27B-1.0-MTP-Abliterated-GGUF
  13. text generation model by Kujira · gguf

    Stale Hugging Face Hub, Kujira 32 ♥apache-2.0Updated 40 days ago

    Kujira/Underdog-Saluki-27B-1.0-MTP-GGUF
  14. Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.

    Indexed OpenRouter model list, qwen Updated 2 months ago

    qwen/qwen3.8-flash
  15. image text to text model by jackjusko · gguf

    Stale Hugging Face Hub, jackjusko 68 ♥otherUpdated 13 days ago

    jackjusko/Swift-1.5-Flash-Next-Heretic-ReverseEngineer
  16. Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...

    Indexed OpenRouter model list, qwen Updated 3 months ago

    qwen/qwen3.8-27b
  17. image text to text model by trubisky · gguf

    Stale Hugging Face Hub, trubisky 59 ♥otherUpdated 18 days ago

    trubisky/Swift-1.5-Flash-Next-Heretic-ReverseEngineer
  18. Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...

    Indexed OpenRouter model list, qwen Updated 3 months ago

    qwen/qwen3.8-27b:batch
  19. unsloth

    AI repositories

    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.

    Indexed GitHub, unslothai 79.6k ★Apache-2.0Updated yesterday

    git clone https://github.com/unslothai/unsloth.git
  20. Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...

    Indexed OpenRouter model list, qwen Updated 57 days ago

    qwen/qwen3.8-omni-flash
  21. ms-swift

    AI repositories

    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).

    Indexed GitHub, modelscope 16.1k ★Apache-2.0Updated 4 days ago

    git clone https://github.com/modelscope/ms-swift.git
  22. halogen-flash-server

    AI repositories

    Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.

    Stale GitHub, peonist-ai 1,258 ★Custom licence (see repository)Updated 9 days ago

    git clone https://github.com/peonist-ai/halogen-flash-server.git
  23. qwen38-free-gateway

    MCP servers

    Free Qwen3.8-27B gateway with isolated Minis provider, SSE, retry/failover, and MCP.

    Stale Official MCP Registry, io.github.khs0927 Updated 3 months ago 1 note

  24. strix-halo-guide

    Datasets & benchmarks

    Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results.

    Stale GitHub, hogeheer499-commits 373 ★MITUpdated 8 days ago

    git clone https://github.com/hogeheer499-commits/strix-halo-guide.git

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.