GGUF models by eugenehp
35 GGUF models quantized by eugenehp on Hugging Face. Sizes run from 4M to 26.9B parameters. The longest trained context is 256K tokens.
About eugenehp on Hugging Face
eugenehp has published 35 GGUF models that ggufmodels.com tracks, across families such as Zipvoice, Siglip and Qwen. The most downloaded are Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled, kokoro 82m and Llama3-8B-1.58-100B-tokens.
The quants eugenehp publishes most often are F16 (21), Q4_K_M (6), F32 (4) and Q8_0 (3). Their Q4_K_M files range from 0.3 to 16.5 GB. Parameter counts run from 4M to 26.9B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has eugenehp published?
35 models are listed here, mainly from the Zipvoice, Siglip and Qwen families. The most downloaded is Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled.
Which quants does eugenehp publish?
The most common are F16 (21 models), Q4_K_M (6 models), F32 (4 models) and Q8_0 (3 models).