GGUF models by Volko76
34 GGUF models quantized by Volko76 on Hugging Face. Sizes run from 268M to 284B parameters. The longest trained context is 1024K tokens.
QW
Qwen3.5-122B-A10B
Qwen · Volko76
Params122B
Context256K
Smallest60.2 GB
LL
Meta Llama 3 8B Instruct
Llama · Volko76
Params8.03B
Context8K
Q4_K_M4.9 GB
GE
gemma 3 270m it imatrix
Gemma · Volko76
Params270M
Context—
Smallest0.0 GB
QW
Fablia Qwen3 1.7B
Qwen · Volko76
Params1.72B
Context40K
Q4_K_M1.1 GB