GGUF models by BoscoTheDog
58 GGUF models quantized by BoscoTheDog on Hugging Face. Sizes run from 121M to 9.24B parameters. The longest trained context is 128K tokens.
About BoscoTheDog on Hugging Face
BoscoTheDog has published 58 GGUF models that ggufmodels.com tracks, across families such as Phi, Gemma and Mistral. The most downloaded are phi 3 mini 128k it russian Q4 K M chunked, h2o-danube3-500m-chat and bitnet_b1_58-xl.
The quants BoscoTheDog publishes most often are Q4_K_M (23), Q4_0 (11), Q8_0 (10) and Q5_K_M (9). Their Q4_K_M files range from 0.2 to 5.0 GB. Parameter counts run from 121M to 9.24B, and the longest trained context window is 128K tokens.
Frequently asked questions
What GGUF models has BoscoTheDog published?
58 models are listed here, mainly from the Phi, Gemma and Mistral families. The most downloaded is phi 3 mini 128k it russian Q4 K M chunked.
Which quants does BoscoTheDog publish?
The most common are Q4_K_M (23 models), Q4_0 (11 models), Q8_0 (10 models) and Q5_K_M (9 models).