GGUF models by smarttasks
36 GGUF models quantized by smarttasks on Hugging Face. Sizes run from 23M to 30.5B parameters. The longest trained context is 256K tokens.
About smarttasks on Hugging Face
smarttasks has published 36 GGUF models that ggufmodels.com tracks, across families such as Qwen, Gemma and BGE. The most downloaded are Qwen_Qwen2.5 Coder 7B Instruct, Qwen_Qwen3 Coder 30B A3B Instruct and Qwen_Qwen2.5 Coder 14B Instruct.
The quants smarttasks publishes most often are Q8_0 (34), Q5_K_M (34), Q4_K_M (34) and Q6_K (25). Their Q4_K_M files range from 0.0 to 18.6 GB. Parameter counts run from 23M to 30.5B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has smarttasks published?
36 models are listed here, mainly from the Qwen, Gemma and BGE families. The most downloaded is Qwen_Qwen2.5 Coder 7B Instruct.
Which quants does smarttasks publish?
The most common are Q8_0 (34 models), Q5_K_M (34 models), Q4_K_M (34 models) and Q6_K (25 models).