IQ1_S GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 25491 models have a IQ1_S file. Sizes run from 2M to 2780B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.8-27B
Qwen · unsloth
Params27.3B
Context256K
Q4_K_M16.5 GB
Vision
QW
Qwen3.8 Flash Next
Qwen · unsloth
Params177B
Context256K
Q4_K_M1.9 GB
Vision
CY
Cyber Ornith 1.5 9B OBLITERATED
Cyber · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
GL
GLM 5.3 Flash
GLM · unsloth
Params320B
Context1024K
Smallest93.1 GB
Vision
IN
Inkling-Small
Inkling · unsloth
Params264B
Context1024K
Q4_K_M162.5 GB
ReasoningVision
QW
Qwen3-4B
Qwen · unsloth
Params4B
Context40K
Q4_K_M2.5 GB
GGUF
QW
Qwen3-Coder-30B-A3B-Instruct
Qwen · unsloth
Params30.5B
Context256K
Q4_K_M18.6 GB
Coding
QW
Qwen3-4B-Instruct-2507
Qwen · unsloth
Params4B
Context256K
Q4_K_M2.5 GB
GGUF
QW
Qwen3-Vl-4B-Instruct
Qwen · unsloth
Params4B
Context256K
Q4_K_M2.5 GB
Vision
QW
Qwen3-30B-A3B-Instruct-2507
Qwen · unsloth
Params30.5B
Context256K
Q4_K_M18.6 GB
GGUF
GL
GLM 5.3
GLM · unsloth
Params754B
Context1024K
Smallest216.7 GB
GGUF
IN
TML Inkling
Inkling · unsloth
Params950B
Context1024K
Smallest270.2 GB
ReasoningVision
KI
Kimi-K3
Kimi · unsloth
Params2780B
Context1024K
Smallest466.4 GB
Vision
QW
Qwen2.5-Vl-7B-Instruct
Qwen · unsloth
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
LI
Ling 3.0 Tiny
Ling · bloomer010
Params7.89B
Context128K
Q4_K_M4.8 GB
Coding
GL
Glm-4.7-Flash
GLM · unsloth
Params30B
Context198K
Q4_K_M18.3 GB
GGUF
LI
Ling 3.0 Flash
Ling · AtomicChat
Params124B
Context128K
Q4_K_M75.3 GB
ReasoningTool use
DE
DeepSeek V4.1 Flash 1017
DeepSeek · unsloth
Params748B
Context1024K
Smallest8.0 GB
GGUF
QW
Qwen3-1.7B
Qwen · unsloth
Params1.72B
Context40K
Q4_K_M1.1 GB
GGUF
QW
Qwen3-Vl-8B-Instruct
Qwen · unsloth
Params8.19B
Context256K
Q4_K_M5.0 GB
Vision
LL
Llama-3.2-3B-Instruct
Llama · unsloth
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
QW
Swift 1.5 Qwen3.8 Flash Next
Qwen · ukisai
Params177B
Context256K
Q4_K_M119.6 GB
ReasoningVision
DE
Deepseek-R1-0528-Qwen3-8B
DeepSeek · unsloth
Params8.19B
Context128K
Q4_K_M5.0 GB
Reasoning
QW
Qwen3-Coder-Next
Qwen · unsloth
Params80B
Context256K
Q4_K_M48.5 GB
Coding
QW
Qwen3-0.6B
Qwen · unsloth
Params596M
Context40K
Q4_K_M0.4 GB
GGUF
DE
DeepSeek V4 Flash 0731
DeepSeek · unsloth
Params284B
Context—
Smallest10.9 GB
GGUF
GL
GLM 5.2
GLM · unsloth
Params754B
Context1024K
Q4_K_M465.8 GB
GGUF
QW
Qwen3-8B
Qwen · unsloth
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
DE
DeepSeek V4.1 Flash 1017 Maya
DeepSeek · peasantsmith
Params748B
Context—
Smallest276.6 GB
GGUF
GE
Gemma-3-4B-It
Gemma · unsloth
Params3.88B
Context128K
Q4_K_M2.5 GB
Vision

What is IQ1_S?

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. On average it stores about 1.6 bits per weight, so a IQ1_S file is roughly 10% of the size of the same model in 16-bit. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

25,491 models have a IQ1_S file on ggufmodels.com, and those files range from 0.0 to 594.0 GB. The most downloaded are Qwen3.8-27B, Qwen3.8 Flash Next and Cyber Ornith 1.5 9B OBLITERATED. For a longer explanation of every quant type, read GGUF quantization explained.

Frequently asked questions

What is IQ1_S in GGUF?

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. It averages about 1.6 bits per weight.

Should I use IQ1_S?

Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

How big is a IQ1_S file?

IQ1_S files on this site range from 0.0 to 594.0 GB, depending on the model. As a rule of thumb it is about 10% of the 16-bit size.

Other quants

Keep browsing