Undi95/MG-FinalMix-72B GGUF Quantizations πŸš€

Featherless AI Quants

Optimized GGUF quantization files for enhanced model performance

Powered by Featherless AI - run any model you'd like for a simple small fee.


Available Quantizations πŸ“Š

Quantization Type File Size
IQ4_XS Undi95-MG-FinalMix-72B-IQ4_XS 38302.65 MB (folder)
Q2_K Undi95-MG-FinalMix-72B-Q2_K 28430.71 MB (folder)
Q3_K_L Undi95-MG-FinalMix-72B-Q3_K_L 37675.12 MB (folder)
Q3_K_M Undi95-MG-FinalMix-72B-Q3_K_M 35952.30 MB (folder)
Q3_K_S Undi95-MG-FinalMix-72B-Q3_K_S 32890.12 MB (folder)
Q4_K_M Undi95-MG-FinalMix-72B-Q4_K_M 45219.15 MB (folder)
Q4_K_S Undi95-MG-FinalMix-72B-Q4_K_S 41856.02 MB (folder)
Q5_K_M Undi95-MG-FinalMix-72B-Q5_K_M 51925.15 MB (folder)
Q5_K_S Undi95-MG-FinalMix-72B-Q5_K_S 48995.15 MB (folder)
Q6_K Undi95-MG-FinalMix-72B-Q6_K 61366.68 MB (folder)
Q8_0 Undi95-MG-FinalMix-72B-Q8_0 73683.37 MB (folder)

⚑ Powered by Featherless AI

Key Features

  • πŸ”₯ Instant Hosting - Deploy any Llama model on HuggingFace instantly
  • πŸ› οΈ Zero Infrastructure - No server setup or maintenance required
  • πŸ“š Vast Compatibility - Support for 2400+ models and counting
  • πŸ’Ž Affordable Pricing - Starting at just $10/month

Links:
Get Started | Documentation | Models

Downloads last month
194
GGUF
Model size
72.7B params
Architecture
qwen2

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
Unable to determine this model's library. Check the docs .

Model tree for featherless-ai-quants/Undi95-MG-FinalMix-72B-GGUF

Quantized
(3)
this model