GGUF models by MilyaShams
49 GGUF models quantized by MilyaShams on Hugging Face. Sizes run from 1.72B to 7.61B parameters. The longest trained context is 40K tokens.
QW
Qwen3 1.7B GPTQ W4A16 bs128 damp0.01
Qwen · MilyaShams
Params2.03B
Context40K
Q4_K_M1.3 GB
QW
Qwen3 1.7B SmoothQuant 0.6 PTQ W8A8
Qwen · MilyaShams
Params2.03B
Context40K
Smallest2.2 GB
QW
Qwen3 1.7B PTQ W4A16 ign
Qwen · MilyaShams
Params2.03B
Context40K
Q4_K_M1.3 GB
QW
Qwen3 1.7B Pipe Wanda unstruct 0.5 PTQ W8A8
Qwen · MilyaShams
Params2.03B
Context40K
Smallest2.2 GB
QW
Qwen3 1.7B Pipe SparseGPT unstruct 0.5 SmoothQuant 0.5 PTQ W8A8
Qwen · MilyaShams
Params2.03B
Context40K
Smallest2.2 GB
QW
Qwen3 1.7B AutoRound W4A16 ign
Qwen · MilyaShams
Params1.72B
Context40K
Q4_K_M1.1 GB
QW
Qwen3 1.7B SmoothQuant 0.4 PTQ W8A8
Qwen · MilyaShams
Params2.03B
Context40K
Smallest2.2 GB
QW
Qwen3 1.7B Wanda unstruct 0.4
Qwen · MilyaShams
Params1.72B
Context40K
Smallest3.4 GB
QW
Qwen3 1.7B PTQ W8A8 ign
Qwen · MilyaShams
Params2.03B
Context40K
Smallest2.2 GB
QW
Qwen3 1.7B GPTQ W8A8 bs128 damp0.01
Qwen · MilyaShams
Params2.03B
Context40K
Smallest2.2 GB
QW
Qwen3 1.7B Wanda 1 4
Qwen · MilyaShams
Params1.72B
Context40K
Smallest3.4 GB
QW
Qwen3 1.7B GPTQ W4A16 bs128 damp0.05
Qwen · MilyaShams
Params2.03B
Context40K
Q4_K_M1.3 GB
QW
Qwen3 1.7B AWQ W4A16 ign
Qwen · MilyaShams
Params1.72B
Context40K
Q4_K_M1.1 GB
QW
Qwen3 1.7B SmoothQuant 0.5 PTQ W8A8
Qwen · MilyaShams
Params2.03B
Context40K
Smallest2.2 GB
QW
Qwen3 1.7B SmoothQuant 0.5 PTQ W4A16
Qwen · MilyaShams
Params2.03B
Context40K
Q4_K_M1.3 GB
QW
Qwen3 1.7B SmoothQuant 0.6 PTQ W4A16
Qwen · MilyaShams
Params2.03B
Context40K
Q4_K_M1.3 GB
QW
Qwen3 1.7B PTQ W4A16
Qwen · MilyaShams
Params2.03B
Context40K
Q4_K_M1.3 GB
QW
Qwen3 1.7B PTQ W8A8
Qwen · MilyaShams
Params2.03B
Context40K
Smallest2.2 GB
QW
Qwen3 1.7B GPTQ W8A8 bs128 damp0.05
Qwen · MilyaShams
Params2.03B
Context40K
Smallest2.2 GB