Hugging Face's logo

Spaces:
k-mktr
/
gpu-poor-llm-arena
Running

App Files Community
9

=== MODEL REQUESTS HERE ===

#8
by k-mktr - opened
Discussion
k-mktr
 Owner

Model Request Form

Want to see a new GGUF LLM in the GPU Poor Arena? Use this template to suggest models you'd like us to consider adding!

  1. Model Name (Required):
    [e.g., TheDrummer_Cydonia-24B-v4.1]

  2. Hugging Face GGUF Model Link (Required):
    [Please provide the direct URL to the GGUF model's page on Hugging Face, e.g., https://huggingface.co/bartowski/TheDrummer_Cydonia-24B-v4.1-GGUF]

  3. Why would you like to see this model added? (Optional):
    [Tell us why you think this model would be a great addition to the arena!]

  4. Any other notes or considerations? (Optional):
    [e.g., specific use cases, known issues, or unique features.]

ninjaeon
•
edited 25 days ago

  1. Apriel-1.5-15b-Thinker

  2. https://huggingface.co/unsloth/Apriel-1.5-15b-Thinker-GGUF

ninjaeon

  1. Magistral-Small-2509

  2. https://huggingface.co/unsloth/Magistral-Small-2509-GGUF

sbeltz

  1. Ling-lite-1.5-2507-GGUF

  2. https://huggingface.co/mradermacher/Ling-lite-1.5-2507-GGUF

  3. Fast MoE fits in 12GB RAM, competitive with Qwen3 30B MoE.

  4. Runs at 17 tokens/s on a 2020 CPU, and 38 tokens/s on a 2024 iGPU.

lemon07r

  1. Apriel-1.5-15b-Thinker

  2. https://huggingface.co/unsloth/Apriel-1.5-15b-Thinker-GGUF

  3. IMO its better than the Granite 4.0 small and is a direct competitor at this size.

aquiffoo
  1. aquif-3.5-8B
  2. https://huggingface.co/bartowski/aquif-ai_aquif-3.5-8B-Think-GGUF

Sign up or log in to comment