Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
Jackrong 's Collections
🚀 Qwen-MTP
🍎 Qwopus3.6
🌪️ Negentropy-claude-opus-4.7
🐳 DeepSeek-V4-Distill
Qwen3.5-9B-GLM5.1-Distill
Qwopus3.5-v3.5/v3
Gemopus-4
Qwen3.5-Claude-4.6-Opus-Reasoning-Distilled
Qwen3.5-Claude-4.6-Opus-Reasoning-Distilled-v2
Qwen3.5-Neo
Qwen3.5-Gemini-3.1-Pro-Reasoning-Distilled
DASD
GPT-5-Distill-Qwen3-Lllama3

🚀 Qwen-MTP

updated about 15 hours ago

⚡ MTP (Multi Token Prediction) speculative decoding enables models like Qwen3.6 to have ~1.4-2.2x faster generation with no change in accuracy.

Upvote
5

  • Jackrong/Qwopus3.6-27B-v2-MTP-GGUF

    Text Generation • 27B • Updated 1 day ago • 3.53k • 66

  • Jackrong/Qwopus3.5-9B-Coder-MTP-GGUF

    Text Generation • 9B • Updated 4 days ago • 27.4k • 85

  • Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF

    9B • Updated 2 days ago • 386 • 6

  • Jackrong/Qwopus3.5-4B-v3-MTP-GGUF

    4B • Updated 2 days ago • 294 • 2

  • Jackrong/Qwopus3.6-35B-A3B-v1-MTP-GGUF

    36B • Updated about 15 hours ago • 4
Upvote
5
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs