IQ3_M GGUF models

Importance-matrix 3-bit quant, medium. Aimed at low-memory setups. 47889 models have a IQ3_M file. Sizes run from 1M to 1030B parameters. The longest trained context is 102400K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.8 27B Uncensored HauhauCS Aggressive MTP
Qwen · HauhauCS
Params30B
Context—
Smallest0.9 GB
GGUF
QW
Qwen3.5 9B The Defiant Fable Uncensored Heretic NEO IMATRIX MAX MTP
Qwen · DavidAU
Params8.95B
Context256K
Q4_K_M6.8 GB
CodingReasoningRoleplay
QW
Qwen3.8 27B TURBO Fable Cold Fusion 735 882 Heretic Uncensored NEO CODER MAX MTP
Qwen · DavidAU
Params27B
Context256K
Q4_K_M18.0 GB
CodingReasoningRoleplay
QW
Qwen3.8 35B A3B Distill
Qwen · empero-ai
Params35.5B
Context256K
Q4_K_M21.7 GB
ReasoningVision
QW
Qwen3.8 Flash Next Uncensored
Qwen · orcarouter
Params177B
Context256K
Q4_K_M119.2 GB
ReasoningTool useVision
QW
MiMo V2.6 Distill Qwen 9B
Qwen · bartowski
Params8.95B
Context256K
Q4_K_M5.8 GB
CodingTool useVision
QW
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
Qwen · HauhauCS
Params34.7B
Context256K
Q4_K_M21.2 GB
Vision
GE
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
Gemma · HauhauCS
Params7.5B
Context128K
Q4_K_M5.3 GB
Vision
QW
Qwen2.5 32B Instruct
Qwen · bartowski
Params32.8B
Context32K
Q4_K_M19.9 GB
GGUF
CY
Cyber Ornith 1.5 9B OBLITERATED
Cyber · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
OC
Occamy 1.0
Occamy · Accio-Lab
Params34.7B
Context256K
Q4_K_M21.2 GB
Tool useVision
MU
Muse Glimmer 30B
Muse · unsloth
Params27.9B
Context128K
Smallest1.6 GB
Vision
QW
Qwen3.8 27B
Qwen · DavidAU
Params27B
Context256K
Q4_K_M16.5 GB
CodingReasoningVision
QW
Swift Qwen3.8 27b
Qwen · ukisai
Params27.3B
Context256K
Q4_K_M18.0 GB
ReasoningVision
QW
Qwen3.6 27B Fable Fusion 711 Uncensored Heretic NM DAU NEO MAX MTP
Qwen · DavidAU
Params27B
Context256K
Q4_K_M18.0 GB
CodingReasoningRoleplay
AP
Apodex 1.1 Mini
Apodex · abenzerps
Params35.5B
Context256K
Q4_K_M19.8 GB
Vision
LL
Meta Llama 3.1 8B Instruct
Llama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
BI
BigBang v1
Bigbang · bartowski
Params35.5B
Context256K
Q4_K_M21.9 GB
Vision
QW
Qwen3.8 27B Cold Fusion GAIN V1.1 NM DAU NEO MAX MTP
Qwen · DavidAU
Params27B
Context256K
Q4_K_M18.0 GB
CodingReasoningRoleplay
TH
Thomson 1.0 Small
Thomson · bartowski
Params34.7B
Context256K
Q4_K_M21.4 GB
Vision
LF
LFM2.5 24B A2B
Lfm · DavidAU
Params24B
Context128K
Smallest10.5 GB
CodingReasoning
KA
KAT Coder V2.5 Dev
Kat · bartowski
Params34.7B
Context256K
Q4_K_M21.4 GB
Coding
QW
Qwen3.8 27B
Qwen · bartowski
Params27.3B
Context256K
Q4_K_M17.4 GB
Vision
MI
MiniCPM V 4.7 35B A3B
MiniCPM · openbmb
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
QW
Qwen2.5 7B Instruct
Qwen · bartowski
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
LI
Ling 3.0 Flash
Ling · AtomicChat
Params124B
Context128K
Q4_K_M75.3 GB
ReasoningTool use
QW
Swift 1.5 Qwen3.8 27B
Qwen · ukisai
Params27.3B
Context256K
Q4_K_M17.4 GB
ReasoningVision
QW
Qwen3.5 9B
Qwen · bartowski
Params9.2B
Context256K
Q4_K_M6.2 GB
Vision
LF
LFM2.5 24B A2B Uncensored
Lfm · AtomicChat
Params24B
Context128K
Q4_K_M15.4 GB
ReasoningTool use
QW
Qwen3.6 35B A3B
Qwen · bartowski
Params35.5B
Context256K
Q4_K_M22.3 GB
Vision

What is IQ3_M?

Importance-matrix 3-bit quant, medium. Aimed at low-memory setups. On average it stores about 3.7 bits per weight, so a IQ3_M file is roughly 23% of the size of the same model in 16-bit. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

47,889 models have a IQ3_M file on ggufmodels.com, and those files range from 0.0 to 488.1 GB. The most downloaded are Qwen3.8 27B Uncensored HauhauCS Aggressive MTP, Qwen3.5 9B The Defiant Fable Uncensored Heretic NEO IMATRIX MAX MTP and Qwen3.8 27B TURBO Fable Cold Fusion 735 882 Heretic Uncensored NEO CODER MAX MTP. For a longer explanation of every quant type, read GGUF quantization explained.

Frequently asked questions

What is IQ3_M in GGUF?

Importance-matrix 3-bit quant, medium. Aimed at low-memory setups. It averages about 3.7 bits per weight.

Should I use IQ3_M?

A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

How big is a IQ3_M file?

IQ3_M files on this site range from 0.0 to 488.1 GB, depending on the model. As a rule of thumb it is about 23% of the 16-bit size.

Other quants

Keep browsing