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.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3 1.7B SparseGPT unstruct 0.3 bs128 damp0.01
Qwen · MilyaShams
Params1.72B
Context40K
Smallest3.4 GB
GGUF
QW
Qwen3 1.7B SmoothQuant 0.4 AutoRound ign
Qwen · MilyaShams
Params1.72B
Context40K
Smallest1.8 GB
GGUF
QW
Qwen3 1.7B Wanda unstruct 0.1
Qwen · MilyaShams
Params1.72B
Context40K
Smallest3.4 GB
GGUF
QW
Qwen3 1.7B SparseGPT unstruct 0.2 bs128 damp0.01
Qwen · MilyaShams
Params1.72B
Context40K
Smallest3.4 GB
GGUF
QW
Qwen3 1.7B SmoothQuant 0.6 GPTQ W8A8
Qwen · MilyaShams
Params2.03B
Context40K
Smallest2.2 GB
GGUF
QW
Qwen3 1.7B
Qwen · MilyaShams
Params2.03B
Context40K
Smallest4.1 GB
ReasoningTool use
QW
Qwen3 1.7B Pipe SparseGPT unstruct 0.5 GPTQ W4A16
Qwen · MilyaShams
Params2.03B
Context40K
Q4_K_M1.3 GB
GGUF
QW
Qwen3 1.7B AutoRound W8A8 ign
Qwen · MilyaShams
Params1.72B
Context40K
Smallest1.8 GB
GGUF
LI
T Lite It 1.0
Lite · MilyaShams
Params7.61B
Context32K
Q4_K_M4.7 GB
GGUF
QW
Qwen3 1.7B Pipe Wanda unstruct 0.6 AWQ W4A16
Qwen · MilyaShams
Params2.03B
Context40K
Q4_K_M1.3 GB
GGUF
QW
Qwen3 1.7B SmoothQuant 0.5 AWQ W4A16
Qwen · MilyaShams
Params2.03B
Context40K
Q4_K_M1.3 GB
GGUF
QW
Qwen3 1.7B GPTQ W4A16 bs64 damp0.05
Qwen · MilyaShams
Params2.03B
Context40K
Q4_K_M1.3 GB
GGUF
QW
Qwen3 1.7B SparseGPT unstruct 0.1 bs128 damp0.01
Qwen · MilyaShams
Params1.72B
Context40K
Smallest3.4 GB
GGUF
QW
Qwen3 1.7B Wanda unstruct 0.2
Qwen · MilyaShams
Params1.72B
Context40K
Smallest3.4 GB
GGUF
QW
Qwen3 1.7B AWQ W4A16
Qwen · MilyaShams
Params2.03B
Context40K
Q4_K_M1.3 GB
GGUF
QW
Qwen3 1.7B Pipe GPTQ W4A16 SparseGPT unstruct 0.5
Qwen · MilyaShams
Params2.03B
Context40K
Q4_K_M1.3 GB
GGUF
QW
Qwen3 1.7B GPTQ W8A8 bs64 damp0.01
Qwen · MilyaShams
Params2.03B
Context40K
Smallest2.2 GB
GGUF
QW
Qwen3 1.7B SmoothQuant 0.5 GPTQ W4A16
Qwen · MilyaShams
Params2.03B
Context40K
Q4_K_M1.3 GB
GGUF
QW
Qwen3 1.7B SmoothQuant 0.5 AWQ W8A8
Qwen · MilyaShams
Params2.03B
Context40K
Smallest2.2 GB
GGUF
QW
Qwen3 1.7B GPTQ W8A8 bs64 damp0.05
Qwen · MilyaShams
Params2.03B
Context40K
Smallest2.2 GB
GGUF
QW
Qwen3 1.7B Pipe AWQ W4A16 Wanda unstruct 0.6
Qwen · MilyaShams
Params2.03B
Context40K
Q4_K_M1.3 GB
GGUF
QW
Qwen3 1.7B SmoothQuant 0.7 PTQ W8A8
Qwen · MilyaShams
Params2.03B
Context40K
Smallest2.2 GB
GGUF
QW
Qwen3 1.7B Wanda unstruct 0.3
Qwen · MilyaShams
Params1.72B
Context40K
Smallest3.4 GB
GGUF
QW
Qwen3 1.7B SmoothQuant 0.6 AutoRound ign
Qwen · MilyaShams
Params1.72B
Context40K
Smallest1.8 GB
GGUF
QW
Qwen3 1.7B SmoothQuant 0.5 AutoRound W8A8 ign
Qwen · MilyaShams
Params1.72B
Context40K
Smallest1.8 GB
GGUF
QW
Qwen3 1.7B GPTQ W4A16 bs64 damp0.01
Qwen · MilyaShams
Params2.03B
Context40K
Q4_K_M1.3 GB
GGUF
QW
Qwen3 1.7B GPTQ W8A8 bs128 damp0.01 ign
Qwen · MilyaShams
Params1.72B
Context40K
Smallest1.8 GB
GGUF
QW
Qwen3 1.7B Pipe PTQ W8A8 Wanda unstruct 0.5
Qwen · MilyaShams
Params2.03B
Context40K
Smallest2.2 GB
GGUF
QW
Qwen3 1.7B SmoothQuant 0.5 GPTQ W8A8
Qwen · MilyaShams
Params2.03B
Context40K
Smallest2.2 GB
GGUF
QW
Qwen3 1.7B AWQ W8A8
Qwen · MilyaShams
Params2.03B
Context40K
Smallest2.2 GB
GGUF

About MilyaShams on Hugging Face

MilyaShams has published 49 GGUF models that ggufmodels.com tracks, across families such as Qwen and Lite. The most downloaded are Qwen3 1.7B SparseGPT unstruct 0.3 bs128 damp0.01, Qwen3 1.7B SmoothQuant 0.4 AutoRound ign and Qwen3 1.7B Wanda unstruct 0.1.

The quants MilyaShams publishes most often are Q8_0 (22), Q4_K_M (18) and F16 (9). Their Q4_K_M files range from 1.1 to 4.7 GB. Parameter counts run from 1.72B to 7.61B, and the longest trained context window is 40K tokens.

Frequently asked questions

What GGUF models has MilyaShams published?

49 models are listed here, mainly from the Qwen and Lite families. The most downloaded is Qwen3 1.7B SparseGPT unstruct 0.3 bs128 damp0.01.

Which quants does MilyaShams publish?

The most common are Q8_0 (22 models), Q4_K_M (18 models) and F16 (9 models).

Keep browsing