AmpleRun
Deploy

Model catalog

Pick a category, pick a model, and deploy in one click.

Uncensored

Abliterated open-weight models

7 models

  • Dolphin 3.0 Llama 3.1 8B

    8BUncensored

    llama.cpp · Q4_K_M

    • RTX 4090 · 24 GBFastest

      Q4_K_M, Q8, FP16 · needs 8 GB · est. 122–175 tok/s

      Unavailable

    • RTX 3080 Ti · 12 GB

      Q4_K_M, Q8 · needs 8 GB · est. 111–158 tok/s

      Unavailable

    • M1 · 16 GB unified

      Q4_K_M, Q8 · needs 8 GB

      Unavailable

    • M1 Pro · 16 GB unified

      Q4_K_M, Q8 · needs 8 GB · est. 24–35 tok/s

      Unavailable

    16 more

    View details

  • Huihui Mistral Small 24B abliterated

    24BUncensored

    llama.cpp · Q4_K_M

    • RTX 4090 · 24 GBFastest

      Q4_K_M · needs 22 GB · est. 42–60 tok/s

      Unavailable

    • M4 Pro · 24 GB unified

      Q4_K_M · needs 22 GB · est. 11–17 tok/s

      Unavailable

    • RTX 3090 · 24 GB

      Q4_K_M · needs 22 GB · est. 39–56 tok/s

      Unavailable

    • RX 7900 XTX · 24 GB

      Q4_K_M · needs 22 GB

      Unavailable

    7 more

    View details

  • Huihui Qwen3 14B abliterated

    14BUncensored

    llama.cpp · Q4_K_M

    • RTX 4090 · 24 GBFastest

      Q4_K_M, Q8 · needs 11 GB · est. 67–96 tok/s

      Unavailable

    • RTX 3080 Ti · 12 GB

      Q4_K_M · needs 11 GB · est. 60–87 tok/s

      Unavailable

    • M1 · 16 GB unified

      Q4_K_M · needs 11 GB

      Unavailable

    • M1 Pro · 16 GB unified

      Q4_K_M · needs 11 GB · est. 13–19 tok/s

      Unavailable

    16 more

    View details

  • Huihui QwQ 32B abliterated

    32BUncensored

    llama.cpp · Q4_K_M

    • RTX 4090 · 24 GBFastest

      Q4_K_M · needs 22 GB · est. 30–44 tok/s

      Unavailable

    • M4 Pro · 24 GB unified

      Q4_K_M · needs 22 GB · est. 8–12 tok/s

      Unavailable

    • RTX 3090 · 24 GB

      Q4_K_M · needs 22 GB · est. 28–41 tok/s

      Unavailable

    • RX 7900 XTX · 24 GB

      Q4_K_M · needs 22 GB

      Unavailable

    7 more

    View details

  • Qwen2.5 Coder 1.5B abliterated

    1.5BUncensored

    llama.cpp · Q4_K_M

    • RTX 4090 · 24 GBFastest

      Q4_K_M, Q8, FP16 · needs 4 GB · est. 541–767 tok/s

      Unavailable

    • RTX 3080 Ti · 12 GB

      Q4_K_M, Q8, FP16 · needs 4 GB · est. 489–694 tok/s

      Unavailable

    • M1 · 16 GB unified

      Q4_K_M, Q8, FP16 · needs 4 GB

      Unavailable

    • M1 Pro · 16 GB unified

      Q4_K_M, Q8, FP16 · needs 4 GB · est. 107–153 tok/s

      Unavailable

    16 more

    View details

  • Qwen3.8 27B Uncensored

    27BUncensored

    llama.cpp · Q4_K_M

    • RTX 4090 · 24 GBFastest

      Q4_K_M · needs 22 GB · est. 34–49 tok/s

      Unavailable

    • M4 Pro · 24 GB unified

      Q4_K_M · needs 22 GB · est. 9–14 tok/s

      Unavailable

    • RTX 3090 · 24 GB

      Q4_K_M · needs 22 GB · est. 31–45 tok/s

      Unavailable

    • RX 7900 XTX · 24 GB

      Q4_K_M · needs 22 GB

      Unavailable

    7 more

    View details

  • SmolLM2 1.7B Uncensored

    1.7BUncensored

    llama.cpp · Q4_K_M

    • RTX 4090 · 24 GBFastest

      Q4_K_M, Q8, FP16 · needs 8 GB · est. 543–771 tok/s

      Unavailable

    • RTX 3080 Ti · 12 GB

      Q4_K_M, Q8, FP16 · needs 8 GB · est. 491–697 tok/s

      Unavailable

    • M1 · 16 GB unified

      Q4_K_M, Q8, FP16 · needs 8 GB

      Unavailable

    • M1 Pro · 16 GB unified

      Q4_K_M, Q8, FP16 · needs 8 GB · est. 107–153 tok/s

      Unavailable

    16 more

    View details

Deploy any Hugging Face model

Paste a repo URL or ID like Qwen/Qwen3-32B. We'll estimate VRAM and suggest an engine.

Not sure what runs on your machine? See what fits.