GGUF models by Iambackup
38 GGUF models quantized by Iambackup on Hugging Face. Sizes run from 1.08B to 121B parameters. The longest trained context is 10240K tokens.
About Iambackup on Hugging Face
Iambackup has published 38 GGUF models that ggufmodels.com tracks, across families such as Gemma, Phi and Llama. The most downloaded are QwQ 32B Preview abliterated, Gemma-4-12B-OBLITERATED-v2 and Phi 3 mini 128k instruct abliterated v3.
The quants Iambackup publishes most often are Q6_K (22), Q8_0 (21), Q5_K_M (10) and Q4_K_M (8). Their Q4_K_M files range from 0.7 to 19.9 GB. Parameter counts run from 1.08B to 121B, and the longest trained context window is 10240K tokens.
Frequently asked questions
What GGUF models has Iambackup published?
38 models are listed here, mainly from the Gemma, Phi and Llama families. The most downloaded is QwQ 32B Preview abliterated.
Which quants does Iambackup publish?
The most common are Q6_K (22 models), Q8_0 (21 models), Q5_K_M (10 models) and Q4_K_M (8 models).