GGUF models by tensorblock
4944 GGUF models quantized by tensorblock on Hugging Face. Sizes run from 1M to 72.7B parameters. The longest trained context is 1024K tokens.
About tensorblock on Hugging Face
tensorblock has published 4,944 GGUF models that ggufmodels.com tracks, across families such as Llama, Qwen and Mistral. The most downloaded are Qwen Qwen1.5 MoE A2.7B Chat, Qwen Qwen3 Coder 30B A3B Instruct and magnum v4 12b.
The quants tensorblock publishes most often are Q2_K (4911), Q3_K_M (1561), BF16 (31) and F16 (2). Parameter counts run from 1M to 72.7B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has tensorblock published?
4,944 models are listed here, mainly from the Llama, Qwen and Mistral families. The most downloaded is Qwen Qwen1.5 MoE A2.7B Chat.
Which quants does tensorblock publish?
The most common are Q2_K (4911 models), Q3_K_M (1561 models), BF16 (31 models) and F16 (2 models).